149 Pull requests merged by 50 people

• support mimi model export

  #9522 merged Mar 22, 2025

• Make export llama checkpoint and param optional

  #9456 merged Mar 22, 2025

• Fix xnnpack quantization discrepancy for non-fp32

  #8488 merged Mar 22, 2025

• Enable optimized op_le broadcast against 1 element tensor

  #9507 merged Mar 22, 2025

• Use gradle to build the AAR

  #9382 merged Mar 22, 2025

• Fix * 4 debug fix that got accidentally landed in op_sdpa.cpp

  #9492 merged Mar 22, 2025

• Use xplat/caffe2:ovrsource_aten_Config.h for arvr build modes

  #9462 merged Mar 22, 2025

• Remove tuple from module implementation

  #9519 merged Mar 22, 2025

• Export Mimi to xnnpack

  #9303 merged Mar 21, 2025

• [ExecuTorch] Add //examples/portable/executor_runner:executor_runner_opt

  #9508 merged Mar 21, 2025

• [ExecuTorch] Add //examples/portable/executor_runner:executor_runner_opt

  #9291 merged Mar 21, 2025

• Handle value and tensor errors as NSErrors keeping the underlying error codes

  #9503 merged Mar 21, 2025

• [Android] Use new Llm package API

  #9495 merged Mar 21, 2025

• Remove Per-Op mode from DQPartitioner

  #9502 merged Mar 21, 2025

• [backend_api] Delete partitioner tags after lowering

  #9501 merged Mar 21, 2025

• Fix lint violation from #9073

  #9496 merged Mar 21, 2025

• Expose ET errors as is

  #9497 merged Mar 21, 2025

• Refactor dtype handling in export_llama

  #9430 merged Mar 21, 2025

• Remove Per-Op mode from DQPartitioner

  #9378 merged Mar 21, 2025

• [backend_api] Delete partitioner tags after lowering

  #9435 merged Mar 21, 2025

• [Android benchmark] Increase cool down time to 180

  #9480 merged Mar 21, 2025

• Arm backend: support int16 and int32 output tables.

  #9359 merged Mar 21, 2025

• Arm backend: Add test pipeline for run_transform_for_annotation_pipeline

  #9488 merged Mar 21, 2025

• Arm backend: Add info about setup_path.sh and arm-none-eabi-gcc

  #9454 merged Mar 21, 2025

• Arm backend: Various fixes to get per channel quantization in place

  #9487 merged Mar 21, 2025

• Migrate java api

  #9478 merged Mar 21, 2025

• Introduce event_tracer_filter_base class

  #9467 merged Mar 21, 2025

• Arm backend: Make setup.sh handle unset EULA variable

  #9446 merged Mar 21, 2025

• [ExecuTorch][XNNPACK] validate quant params before lowering

  #9436 merged Mar 21, 2025

• [Executorch][SDPA] Fix bug in sdpa

  #9479 merged Mar 21, 2025

• CoreML doc updates

  #9463 merged Mar 21, 2025

• Handle case when native_schema is None

  #9377 merged Mar 21, 2025

• Make nightly versions consistent

  #9453 merged Mar 21, 2025

• Fix pyre issues from non-mypy dirs

  #9477 merged Mar 21, 2025

• Upgrade cmake on CI

  #9471 merged Mar 21, 2025

• Run android-perf more frequently

  #9475 merged Mar 20, 2025

• Link quantized ops lib in xnn_executor_runner

  #9443 merged Mar 20, 2025

• [Executorch][SDPA] Fix bug in sdpa

  #9105 merged Mar 20, 2025

• Add the execution permission after the runner file copied to android device.

  #9073 merged Mar 20, 2025

• Do not require checkpoint in quantize() unless it's gptq

  #9470 merged Mar 20, 2025

• Applied quantization for linear with bias=True in pre_quantization

  #9472 merged Mar 20, 2025

• Bump torchao + add unit tests for torchao kernels

  #9396 merged Mar 20, 2025

• [ET-VK][ez] Make sure vTensor is not referencing the global context

  #9469 merged Mar 20, 2025

• Return result from get_backend_name

  #9465 merged Mar 20, 2025

• [ET-VK][ez] Make sure vTensor is not referencing the global context

  #9458 merged Mar 20, 2025

• Collect Named Data Store at construction

  #9370 merged Mar 20, 2025

• [Android docs] Add maven part

  #9442 merged Mar 20, 2025

• [ET-VK][ez] Fix using a temporary variable when creating ComputePipeline

  #9464 merged Mar 20, 2025

• Fix copy pasta error for the error domain

  #9461 merged Mar 20, 2025

• [ET-VK][ez] Fix using a temporary variable when creating ComputePipeline

  #9405 merged Mar 20, 2025

• Arm backend: Fix flaky test LSTM by bumping allowed atol/rtol slightly

  #9452 merged Mar 20, 2025

• Check for nullptr in MethodMeta::uses_backend

  #9457 merged Mar 20, 2025

• Arm backend: Refactor Ops Tests for AvgPool, Clamp, Clone, Conv1d, Sub

  #9039 merged Mar 20, 2025

• Add Android build-tools;35.0.0

  #9429 merged Mar 20, 2025

• Add Module API to query for the number of methods

  #9441 merged Mar 20, 2025

• MethodMeta API to query of backends number and names

  #9440 merged Mar 20, 2025

• [Cadence] Add scalar cases for binary ops (add, mul, sub, div) on HiFi

  #9411 merged Mar 20, 2025

• Keep LiftedConstant in .pte

  #9202 merged Mar 20, 2025

• [ET-VK] Adding all tensor packing support to split op.

  #9439 merged Mar 20, 2025

• [ET-VK] Adding boolean parameters to add_copy_offset_node to specify index calculation function in copy op's shader.

  #9437 merged Mar 20, 2025

• Arm backend: Add WhyNoPartitionReporter and report rejected nodes

  #8963 merged Mar 20, 2025

• Remove proprietary license

  #9389 merged Mar 20, 2025

• Arm backend: Limit number of build jobs

  #9444 merged Mar 20, 2025

• Arm backend: improve common.parameterize decorator

  #9358 merged Mar 20, 2025

• Add SmolLM (smollm2)

  #9354 merged Mar 20, 2025

• [ET-VK] Adding source_offset processing to copy_packed_dim_offset function.

  #9438 merged Mar 20, 2025

• [ET-VK] Adding all tensor packing support to split op.

  #9345 merged Mar 20, 2025

• [ET-VK] Adding source_offset processing to copy_packed_dim_offset function.

  #9344 merged Mar 20, 2025

• [ET-VK] Adding boolean parameters to add_copy_offset_node to specify index calculation function in copy op's shader.

  #9343 merged Mar 20, 2025

• [ExecuTorch][XNNPACK] validate quant params before lowering

  #9299 merged Mar 20, 2025

• Remove protocols and make executorch runtime bridge standalone

  #9398 merged Mar 20, 2025

• [build Folder Migration] Move iOS CI test files

  #9425 merged Mar 20, 2025

• [build Folder Migration] Move wheel files

  #9418 merged Mar 20, 2025

• [build Folder Migration] Move miscellaneous files

  #9417 merged Mar 20, 2025

• fix number of operator error issue

  #9263 merged Mar 19, 2025

• [XNNPACK][Weights Cache] Use sha256 hash of bytes instead of tensor name

  #9413 merged Mar 19, 2025

• install android ndk for mediatek docker

  #9407 merged Mar 19, 2025

• Fix etdump test

  #9410 merged Mar 19, 2025

• [XNNPACK][Weights Cache] Use sha256 hash of bytes instead of tensor name

  #9333 merged Mar 19, 2025

• [trunk.yml] Increase RAM for Arm runners

  #9409 merged Mar 19, 2025

• Add basic ambiguity check in the tests

  #9371 merged Mar 19, 2025

• Create the foundation for testing CoreML export for wheels

  #9381 merged Mar 19, 2025

• Use -fsanitize=address,undefined in debug builds on CI

  #9397 merged Mar 19, 2025

• Remove usage of external flatc in builds and scripts

  #9306 merged Mar 19, 2025

• [ExecuTorch] Arm Ethos:Make get_compile_spec() configurable

  #9403 merged Mar 19, 2025

• [ExecuTorch] Arm Ethos: Add Linear operator tests

  #9402 merged Mar 19, 2025

• [ExecuTorch] Arm Ethos: Do not depend on torch.testing._internal

  #9401 merged Mar 19, 2025

• [ExecuTorch] Arm Ethos:Make get_compile_spec() configurable

  #9323 merged Mar 19, 2025

• [ExecuTorch] Arm Ethos: Add Linear operator tests

  #9322 merged Mar 19, 2025

• use datasink in example runner

  #8920 merged Mar 19, 2025

• [ExecuTorch] Arm Ethos: Do not depend on torch.testing._internal

  #9321 merged Mar 19, 2025

• Support MPS Backend also on iOS < 16 (#9089)

  #9095 merged Mar 19, 2025

• [ET-VK] Adding all tensor packing support to cat op.

  #9380 merged Mar 19, 2025

• Arm backend: Add initial Llama model test case

  #8679 merged Mar 19, 2025

• [build Folder Migration] Move build/build_android_instrumentation.sh

  #9383 merged Mar 19, 2025

• test(etdump): Add FileDataSink test coverage

  #9332 merged Mar 19, 2025

• [ET-VK] Minor performance improvement to permute op.

  #9379 merged Mar 19, 2025

• Use parallel_for in functional_util's apply_unary_map_fun

  #9348 merged Mar 18, 2025

• Use parallel_for in elementwise_util

  #9243 merged Mar 18, 2025

• [ET-VK] Adding all tensor packing support to cat op.

  #9331 merged Mar 18, 2025

• [ET-VK] Minor performance improvement to permute op.

  #9330 merged Mar 18, 2025

• Fix build_apple_frameworks.sh buck resolution

  #9372 merged Mar 18, 2025

• Revert "Arm backend: add tosa_spec and et-version info to .tosa files"

  #9375 merged Mar 18, 2025

• Revert "Arm backend: use dbg_fail when node visitors raise exceptions"

  #9376 merged Mar 18, 2025

• [cadence][g3] link m3 ops and add testcases (#8824)

  #9289 merged Mar 18, 2025

• Test MV3 model in CI wheel builds

  #9192 merged Mar 18, 2025

• Unbreak BroadcastIndexesRange::operator+= when there is no broadcasting

  #9374 merged Mar 18, 2025

• [Android benchmark] Increase sleep time

  #9346 merged Mar 18, 2025

• remove BUCK target for OSS sample tests

  #9328 merged Mar 18, 2025

• Use resolve_buck script to find buck executable when building Apple f…

  #9369 merged Mar 18, 2025

• Add linter for LICENSE

  #9275 merged Mar 18, 2025

• Make BroadcastIndexesRange efficient if there is no broadcasting

  #9298 merged Mar 18, 2025

• executor_runner: print total execution time

  #9342 merged Mar 18, 2025

• re-initialize inputs on each execution in executor_runner

  #9340 merged Mar 18, 2025

• Arm backend: Test popular torch modules/ functions, adress issues

  #9221 merged Mar 18, 2025

• don't copy input std::function in thread_parallel

  #9339 merged Mar 18, 2025

• Fix license to BSD in ExecutorchRuntimeBridge/Exported/Data/ExecutorchRuntimeValue

  #9361 merged Mar 18, 2025

• Fixing issues with Cadence lincense banner

  #9360 merged Mar 18, 2025

• [build Folder Migration] Move buck scripts for cmake

  #9336 merged Mar 18, 2025

• Arm backend: Fix output_folder not created issue in scripts

  #9269 merged Mar 18, 2025

• Arm backend: use dbg_fail when node visitors raise exceptions

  #9268 merged Mar 18, 2025

• Arm backend: add tosa_spec and et-version info to .tosa files

  #9308 merged Mar 18, 2025

• raise reasonable error when verifing program w/o expected outputs

  #9347 merged Mar 18, 2025

• Add null runtime check for XNNExecutor::prepare_args

  #9265 merged Mar 18, 2025

• Fix benchmark job and apple demo app job

  #9329 merged Mar 18, 2025

• Set fbjni version to be 0.5.1

  #9337 merged Mar 17, 2025

• Fix link in android docs

  #9335 merged Mar 17, 2025

• [build Folder Migration] Move build/Utils.cmake

  #9316 merged Mar 17, 2025

• Update swiftpm pin for the demo app

  #9334 merged Mar 17, 2025

• [Benchmark] Generate benchmark record for job failure

  #9247 merged Mar 17, 2025

• Fix optional graph_signature access in memory planning

  #9325 merged Mar 17, 2025

• Qualcomm AI Engine Direct - XR model mld_a enablement

  #9129 merged Mar 17, 2025

• Link extension threadpool with XNNPACK backend instead of custom kernels

  #9327 merged Mar 17, 2025

• Move constraints out of build

  #9320 merged Mar 17, 2025

• Milestone 3 release for operators on FusionG3

  #8824 merged Mar 17, 2025

• Simplify android-release-artifacts.yml

  #9305 merged Mar 17, 2025

• removed malloc and used allocate_temp to allocate memory

  #8026 merged Mar 17, 2025

• [build Folder Migration] Move build/executorch-wheel-config.cmake

  #9319 merged Mar 17, 2025

• [build Folder Migration] Move build/executorch-config.cmake

  #9318 merged Mar 17, 2025

• [build Folder Migration] Move build/Test.cmake

  #9317 merged Mar 17, 2025

• [build Folder Migration] Move build/Codegen.cmake (again)

  #9314 merged Mar 17, 2025

• Include custom_ops and XNNPACK in executor_runner if built

  #9248 merged Mar 17, 2025

• Changes to allow the export of functions with no user input.

  #8031 merged Mar 17, 2025

• Remove false positive error message in the executor_runner

  #7170 merged Mar 17, 2025

• Unbreak unittest-buck

  #9315 merged Mar 17, 2025

• Added logic for model_input flag

  #9310 merged Mar 17, 2025

• Arm backend: Don't handle const placeholders in match_arg_ranks_pass

  #9134 merged Mar 17, 2025

• Migrate users of llm tokenizer to use pytorch-labs/tokenizers

  #9114 merged Mar 17, 2025

• Android build script allow skip LLM

  #9304 merged Mar 16, 2025

54 Pull requests opened by 30 people

• Add support for torch.pow in the Arm backend

  #9309 opened Mar 17, 2025

• Qualcomm AI Engine Direct - LPBQ enablement

  #9313 opened Mar 17, 2025

• set -x in build_apple_frameworks.sh

  #9326 opened Mar 17, 2025

• Remove ops with 0 bytes memory allocation in memory profiler. (#6545)

  #9338 opened Mar 17, 2025

• [WIP]Qualcomm AI Engine Direct - Mimi Encoder/Decoder Enablement

  #9349 opened Mar 18, 2025

• [Executorch][llama] Change runner to decouple prompt length from sequence length

  #9350 opened Mar 18, 2025

• [Executorch][kv cache] Make quantized cache return only the updated cache portion

  #9351 opened Mar 18, 2025

• Qualcomm AI Engine Direct - Add submodule quant config setting

  #9355 opened Mar 18, 2025

• Arm backend: Enable mypy lintrunner for backends/arm/test

  #9357 opened Mar 18, 2025

• Arm backend: Make passes preserve and update node metadata

  #9362 opened Mar 18, 2025

• Remove dead test

  #9363 opened Mar 18, 2025

• Make PyTorch headers available in optimized_portable_kernels, define ET_USE_PYTORCH_HEADERS

  #9384 opened Mar 19, 2025

• elementwise_util: don't cast the result of compute_fun back to the common type

  #9385 opened Mar 19, 2025

• Implement unary_ufunc functions using elementwise_util

  #9386 opened Mar 19, 2025

• Refactor elementwise_util: create variants with out_dtypes in template argument list

  #9387 opened Mar 19, 2025

• RFC: Specialize for non-mixed-dtype in elementwise_util

  #9388 opened Mar 19, 2025

• Arm backend: Use dbg_fail when node visitors raise exceptions

  #9391 opened Mar 19, 2025

• Arm backend: Add tosa_spec info to .tosa files

  #9392 opened Mar 19, 2025

• Deprioritize top level -O2 in CMAKE_CXX_FLAGS_RELEASE

  #9394 opened Mar 19, 2025

• Alternative approach to handling memory offset shift

  #9406 opened Mar 19, 2025

• Bump HF version

  #9408 opened Mar 19, 2025

• Reset IO for the multiple iters output accurancy

  #9412 opened Mar 19, 2025

• [ET-VK] Adding repeat support to add_copy_packed_dim_offset_node function.

  #9414 opened Mar 19, 2025

• [ET-VK] Adding all tensor packing support for repeat op.

  #9415 opened Mar 19, 2025

• [ET-VK] Simplify lane offset copy logic in copy_packed_dim_offset shader.

  #9416 opened Mar 19, 2025

• [ET-VK] Moving repeat functionality from copy_packed_dim_offset into a separate repeat shader.

  #9428 opened Mar 19, 2025

• BroadcastIndexesRange: leading 1s don't require true broadcasting

  #9431 opened Mar 20, 2025

• Add vectorization in elementwise_util (not working yet)

  #9432 opened Mar 20, 2025

• [build Folder Migration] Move core build files into scripts

  #9434 opened Mar 20, 2025

• Arm Backend: Add New Silu and SDPA Decomp passes to arm_pass_manager

  #9448 opened Mar 20, 2025

• [etLLM][Config, Part1] Convert Args to DictConfig

  #9450 opened Mar 20, 2025

• Arm backend: Tosa tools update

  #9451 opened Mar 20, 2025

• [Proposal] Support Multiple Prefill + Decode in a loop

  #9466 opened Mar 20, 2025

• [ET-VK][benchmarking][ez] Don't perform copies when benchmarking

  #9468 opened Mar 20, 2025

• Revert "Arm backend: Add initial Llama model test case"

  #9473 opened Mar 20, 2025

• Separate CoreML util and inmemoryfs targets to be reusable

  #9481 opened Mar 21, 2025

• Create a CoreML inmemoryfs pybinding target

  #9482 opened Mar 21, 2025

• Use executorchcoreml built with CMake instead of extra wheel

  #9483 opened Mar 21, 2025

• Use cached PyTorch wheels on MacOS jobs

  #9484 opened Mar 21, 2025

• Fix exir.load/save to handle named data store map

  #9485 opened Mar 21, 2025

• Arm backend: Add all ops not supported on Ethos-U55 to support-check

  #9489 opened Mar 21, 2025

• updte the return type of log_delegation_intermediate_output

  #9493 opened Mar 21, 2025

• Define CMake args and environment variables simultaneously in install script

  #9494 opened Mar 21, 2025

• Arm backend: Refactor any, bitwise, logical tests

  #9499 opened Mar 21, 2025

• Arm backend: Add ComputeConstantOpsAOT pass

  #9504 opened Mar 21, 2025

• Run setup-macos.sh in unittest-macos even in Buck mode

  #9505 opened Mar 21, 2025

• Fix -Wglobal-constructors/-Wshadow for executor_runner targets

  #9509 opened Mar 21, 2025

• Remove NTSTATUS cast

  #9510 opened Mar 21, 2025

• Depend on extension/threadpool, not thread_parallel_interface, in buck

  #9511 opened Mar 21, 2025

• Bug fix in Ethos runtime backend

  #9517 opened Mar 21, 2025

• Add portable ELU implementation + test

  #9520 opened Mar 22, 2025

• Add optimized ELU implementation

  #9521 opened Mar 22, 2025

• Fix scalar (single element tensor) binary ops on HiFi

  #9523 opened Mar 22, 2025

• Android aar update and enable emulator test

  #9524 opened Mar 22, 2025

27 Issues closed by 19 people

• KernelCall failed at instruction 0:16 in operator aten::le.Tensor_out: 0x12

  #9433 closed Mar 22, 2025

• Update Core ML backend docs using backend template

  #8527 closed Mar 21, 2025

• Llama‘s freqs_cos data loss as for convert dtype

  #9393 closed Mar 21, 2025

• torch._dynamo.exc.Unsupported: Unsupported: quantized nyi in meta tensors with fake tensor propagation.

  #8727 closed Mar 21, 2025

• Building from source error

  #9490 closed Mar 21, 2025

• Request of support of aten::__lshift__.Scala and aten::__rshift__.Scala

  #8711 closed Mar 21, 2025

• [Request Help] “torch._dynamo.exc.UserError: Could not guard on data-dependent expression Eq(u77 - 1, 1)"

  #8988 closed Mar 21, 2025

• I want to understand the size of the memory allocated for the forward method on STM32's

  #9447 closed Mar 21, 2025

• The execution permission of qnn_executor_runner file is removed after the runner file copied to android device.

  #9072 closed Mar 20, 2025

• Reproduce/enable DeepSeek R1 Distill Llama 8B

  #7981 closed Mar 20, 2025

• Lifting constants to an external file should not move __lifted_constant_*

  #8809 closed Mar 20, 2025

• [Request Help] I refer the Delegate Debugging document to debug the QLoRA_LLama 3.2-1B model, and want to get the pipeline of linear operation delegation and determine the underlying kernel in XNNPACK

  #9034 closed Mar 20, 2025

• Is Inspector find_total_for_module correct?

  #7200 closed Mar 20, 2025

• example_runner.sh compile error

  #7078 closed Mar 20, 2025

• UNSTABLE trunk / test-arm-backend-delegation / linux-job

  #9399 closed Mar 20, 2025

• UNSTABLE trunk / test-arm-reference-delegation / linux-job

  #9400 closed Mar 20, 2025

• Add SmolLM

  #9324 closed Mar 20, 2025

• Make sure all license headers are BSD license (or compatible)

  #8418 closed Mar 20, 2025

• Fix license headers for MTK backend

  #9279 closed Mar 20, 2025

• Remove the ability to bring your own flatc

  #9145 closed Mar 19, 2025

• Missing FileDataSink test in etdump_flatcc tests

  #9165 closed Mar 19, 2025

• Unable to convert PrunaAI quantized Llama 3.2 3B model to executorch

  #8591 closed Mar 18, 2025

• Fix license headers under "extension/apple/"

  #9280 closed Mar 18, 2025

• Incompatible license in /backends/cadence/hifi/third-party/nnlib/xa_nn_elm_pow_f32.c

  #9272 closed Mar 18, 2025

• XNNExecutor::prepare_args should check for null runtime

  #9131 closed Mar 18, 2025

• DevX: Improve error reporting for benchmark jobs.

  #8125 closed Mar 17, 2025

• ARM backend: --model_input flag in run.sh is not passed to the aot_arm_compiler

  #9226 closed Mar 17, 2025

28 Issues opened by 19 people

• Typo in import path of examples/models/qwen2_5/__init__.py

  #9525 opened Mar 22, 2025

• CoreML palletization works in PT2E flow

  #9518 opened Mar 21, 2025

• Move Int8DynamicActivationIntxWeightConfig out of torchao/experimental.

  #9516 opened Mar 21, 2025

• Document end-to-end quantization journey in ExecuTorch

  #9515 opened Mar 21, 2025

• Move EmbeddingQuantizer to torchao

  #9514 opened Mar 21, 2025

• Migrate backend quantizers/partitioners to use new torchao quant primitives

  #9513 opened Mar 21, 2025

• ExecuTorch backends implement PT2E quantizer for PTQ/QAT

  #9512 opened Mar 21, 2025

• CoreML model works with torch.jit.trace, but not torch.export.export

  #9506 opened Mar 21, 2025

• ExecuTorch Scalar to() supports fewer types than c10::Scalar, breaking source compatibility

  #9500 opened Mar 21, 2025

• I want to understand the allocations made on STM32s by Executorch

  #9491 opened Mar 21, 2025

• [Request help] torch._dynamo.exc.TorchRuntimeError about indices and SymInt

  #9486 opened Mar 21, 2025

• Run arm tests in OSS CI unittest-buck

  #9476 opened Mar 20, 2025

• Support exporting QNN models with Python wheels out-of-the-box

  #9474 opened Mar 20, 2025

• Backend Specific Configuration in Runtime

  #9459 opened Mar 20, 2025

• Add HuggingFace tokenizer to executor runner

  #9455 opened Mar 20, 2025

• [etLLM] New config system to export_llama

  #9449 opened Mar 20, 2025

• ./install_executorch.sh fails on pip due to dependency conflicts

  #9445 opened Mar 20, 2025

• Remove EXECUTORCH_BUILD_HOST_TARGETS

  #9404 opened Mar 19, 2025

• Llama 3.2 3B Core ML poor output quality

  #9395 opened Mar 19, 2025

• Recipe and Input class definition for executorch.export API

  #9366 opened Mar 18, 2025

• exir.load/exir.save is broken after weight sharing (named data store) addition to EdgeProgramManager

  #9365 opened Mar 18, 2025

• Query regarding support of Executorch for ARM Ethos-U65 backend

  #9356 opened Mar 18, 2025

• Qwen2.5-0.5b SpinQuant export .pte fail

  #9353 opened Mar 18, 2025

• iOS Executorch app support ANE acceleration ?

  #9352 opened Mar 18, 2025

• RFC: Decoder only LLM runner API

  #9341 opened Mar 17, 2025

• build_apple_frameworks.sh failed with error : Cell paths `shim/prelude` and `third-party/prelude` had the same alias `prelude`.

  #9312 opened Mar 17, 2025

• Is the QNN backend support the model of Llama 3.2 3B instead of XNNPACK？

  #9311 opened Mar 17, 2025

• (release/0.5) ./install_requirements.sh fails due to conflicting dependencies.

  #9307 opened Mar 16, 2025

70 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Openvino backend for Executorch to enable inference on Intel CPUs, GPUs, NPUs

  #8573 commented on Mar 22, 2025 • 14 new comments

• Add stub impl of json tokenizer to llama runner

  #9112 commented on Mar 17, 2025 • 7 new comments

• Tiny fixes to make gcc pedantic build happy

  #8933 commented on Mar 21, 2025 • 7 new comments

• Add export_llama performance regression test using expected ops

  #9158 commented on Mar 23, 2025 • 5 new comments

• Arm backend: Remove unused github ci git setup

  #8833 commented on Mar 21, 2025 • 2 new comments

• Add type error suppressions for upcoming upgrade

  #5300 commented on Mar 17, 2025 • 1 new comment

• Arm backend: Add missing __init__.py to passes

  #8592 commented on Mar 21, 2025 • 1 new comment

• Qualcomm AI Engine Direct - oss model enablement (EfficientSAM)

  #9266 commented on Mar 21, 2025 • 1 new comment

• Add type error suppressions for upcoming upgrade

  #5352 commented on Mar 21, 2025 • 1 new comment

• Update Codegen.cmake for improved Python package path handling

  #6730 commented on Mar 18, 2025 • 1 new comment

• Enable xnnpack in aten mode

  #9049 commented on Mar 21, 2025 • 1 new comment

• Arm backend: Move ReplaceScalarTensorWithFullPass to transforms

  #8998 commented on Mar 21, 2025 • 1 new comment

• Remove tombstone messages proactively

  #8703 commented on Mar 19, 2025 • 0 new comments

• Refactoring memory planning to allow running multiple algorithms

  #8440 commented on Mar 22, 2025 • 0 new comments

• Support multi-module exports in Inspector and ETRecord

  #8336 commented on Mar 17, 2025 • 0 new comments

• Fix ODR violation due to const-mismatch with eigens gemm definition.

  #8049 commented on Mar 17, 2025 • 0 new comments

• Add MediaTek backend CI

  #7120 commented on Mar 21, 2025 • 0 new comments

• adding suppression tags to improve autodeps noise

  #6645 commented on Mar 17, 2025 • 0 new comments

• Fix fbcode//executorch/backends/arm/quantizer:arm_quantizer type checking test

  #5378 commented on Mar 17, 2025 • 0 new comments

• Add type error suppressions for upcoming upgrade

  #5321 commented on Mar 17, 2025 • 0 new comments

• Add type error suppressions for upcoming upgrade

  #5314 commented on Mar 17, 2025 • 0 new comments

• Switch to new ao quant api for 8da4w (#8501)

  #8772 commented on Mar 17, 2025 • 0 new comments

• Adding new memory plannig algorithm heap_optimized_greedy

  #8773 commented on Mar 21, 2025 • 0 new comments

• Qualcomm AI Engine Direct - Support Qnn IR backend in online preparation

  #8876 commented on Mar 18, 2025 • 0 new comments

• Introduce missing APIs to lower ExportedProgram objects directly

  #8909 commented on Mar 17, 2025 • 0 new comments

• Cleanup XNN delegate post removal of upsample decomposition

  #8910 commented on Mar 21, 2025 • 0 new comments

• Arm backend: Added 8 new unit tests for testing various passes.

  #9037 commented on Mar 21, 2025 • 0 new comments

• [cadence][g3] enable fp32 permute

  #9053 commented on Mar 17, 2025 • 0 new comments

• Add im2row per tensor overload

  #9121 commented on Mar 17, 2025 • 0 new comments

• Support llama3 training

  #9149 commented on Mar 19, 2025 • 0 new comments

• Add small check when input type is a list

  #9186 commented on Mar 18, 2025 • 0 new comments

• Arm backend: Add MobileNet v3 testcase

  #9223 commented on Mar 21, 2025 • 0 new comments

• Arm backend: Add CEIL Operator

  #9267 commented on Mar 21, 2025 • 0 new comments

• [ExecuTorch] Remove xnn_executor_runner

  #9292 commented on Mar 18, 2025 • 0 new comments

• Add Phi-4-mini README.md

  #9302 commented on Mar 18, 2025 • 0 new comments

• [Build] use timespec_get to get current time

  #5252 commented on Mar 22, 2025 • 0 new comments

• Update MediaTek backend docs using backend template

  #8532 commented on Mar 19, 2025 • 0 new comments

• Update Vulkan backend docs using backend template

  #8529 commented on Mar 19, 2025 • 0 new comments

• Update MPS backend docs using backend template

  #8528 commented on Mar 19, 2025 • 0 new comments

• Update Cadence Xtensa backend docs using backend template

  #8533 commented on Mar 19, 2025 • 0 new comments

• Use real image input in demo colab notebook

  #8851 commented on Mar 19, 2025 • 0 new comments

• Populate "Using ExecuTorch on Android" doc page

  #8536 commented on Mar 19, 2025 • 0 new comments

• Could move some repo resources to S3

  #8805 commented on Mar 19, 2025 • 0 new comments

• Update Qualcomm backend docs using backend template

  #8531 commented on Mar 18, 2025 • 0 new comments

• Expose export_llama.py as a library or function able to be called and imported in Python

  #7695 commented on Mar 18, 2025 • 0 new comments

• [Arm] Add e2e tests for quantized rsqrt, and ensure numerical stability of the LUT based impl

  #8035 commented on Mar 18, 2025 • 0 new comments

• Support Kyutai-labs Moshi and Hibiki models

  #8372 commented on Mar 18, 2025 • 0 new comments

• Native Objective‑C/Swift Wrapper for the ExecuTorch Tensor

  #8366 commented on Mar 18, 2025 • 0 new comments

• Llava 1.5 poor output quality in iOS app

  #9183 commented on Mar 17, 2025 • 0 new comments

• Add GenerateFromPoS in Android LLAMA API

  #8290 commented on Mar 17, 2025 • 0 new comments

• BF16 Support

  #9004 commented on Mar 17, 2025 • 0 new comments

• Optimized linear op doesn't support bias

  #8234 commented on Mar 17, 2025 • 0 new comments

• Add Gemma 3

  #9250 commented on Mar 17, 2025 • 0 new comments

• Add type error suppressions for upcoming upgrade

  #5179 commented on Mar 17, 2025 • 0 new comments

• [Build] fix file_data_loader.cpp build issues for windows

  #4899 commented on Mar 17, 2025 • 0 new comments

• [pytorch hash update] update the pinned pytorch hash

  #4589 commented on Mar 23, 2025 • 0 new comments

• Add necessary third party libs

  #3768 commented on Mar 17, 2025 • 0 new comments

• Update deps paths

  #3767 commented on Mar 17, 2025 • 0 new comments

• Refactor binary op partitioner configs under binary op config class

  #9024 commented on Mar 22, 2025 • 0 new comments

• Partitioner to not delegate mixed dtype operators

  #9023 commented on Mar 22, 2025 • 0 new comments

• [v0.6.0] Release Tracker

  #9253 commented on Mar 21, 2025 • 0 new comments

• double free or corruption (out) on running Llava on x86_64

  #4869 commented on Mar 21, 2025 • 0 new comments

• Quantized MobileBert Model Fails with XNNPACK Assertion Error on Android Deployment

  #8994 commented on Mar 21, 2025 • 0 new comments

• Memory Profiling in DevTools

  #8911 commented on Mar 21, 2025 • 0 new comments

• Parallelize portable ops if threadpool is available, with fallback to parallel_for-as-for-loop

  #8932 commented on Mar 21, 2025 • 0 new comments

• Build pip wheel and validate AOT workflow on different backends & host environments in CI

  #9019 commented on Mar 20, 2025 • 0 new comments

• torch._check_is_size is not being recognized by CoreML partitioner

  #9213 commented on Mar 20, 2025 • 0 new comments

• `torchao:` quantization schemes can't find ao lib

  #8937 commented on Mar 20, 2025 • 0 new comments

• [Android] Flatten data structure like dict in arg types

  #8905 commented on Mar 20, 2025 • 0 new comments

• Vectorize optimized_portable_ops versions of portable ops?

  #9241 commented on Mar 20, 2025 • 0 new comments