19 Pull requests merged by 12 people

• Enable {conv3d, conv_transpose3d} + bn fusion in pt2e

  #2212 merged May 15, 2025

• Add CI for Arm Linux

  #2211 merged May 15, 2025

• ROCm mxfp4 Skips

  #2209 merged May 14, 2025

• Add support for KleidiAI int4 kernels on aarch64 Linux

  #2169 merged May 14, 2025

• unbreak CI by fixing MX tests

  #2208 merged May 14, 2025

• Update __init__.py

  #2206 merged May 14, 2025

• Add mx_fp4 path

  #2201 merged May 13, 2025

• Arm_inductor_quantizer for Pt2e quantization

  #2139 merged May 13, 2025

• [float] document e2e training -> inference flow

  #2190 merged May 13, 2025

• Remove sparsity/prototype/blocksparse

  #2205 merged May 13, 2025

• Skips for ROCm (X86 Inductor Tests)

  #2202 merged May 13, 2025

• Add blockwise fp8 gemm benchmarks to README

  #2203 merged May 12, 2025

• Feat: Implementation of the DeepSeek blockwise quantization for fp8 tensors

  #1763 merged May 12, 2025

• Add noindex to 0.10 and 0.9 docs

  #2194 merged May 12, 2025

• Add subclass based method for inference w/ MXFP8

  #2132 merged May 12, 2025

• unpin torch to unbreak mac tests

  #2198 merged May 12, 2025

• 2:4 activation sparsity packing kernels

  #2012 merged May 12, 2025

• Forward fix lint

  #2197 merged May 12, 2025

• Skip ROCm MoE Quantization

  #2191 merged May 12, 2025

9 Pull requests opened by 9 people

• Update GemLite to support vLLM V1

  #2199 opened May 12, 2025

• [WIP]Enable Int4WeightOnlyGPTQQuantizer on Intel GPU.

  #2200 opened May 12, 2025

• [reland2][ROCm] preshuffled weight mm

  #2207 opened May 13, 2025

• primitive scale fix

  #2210 opened May 14, 2025

• Add selective weight loading decode kernel for activation sparsity

  #2213 opened May 15, 2025

• Fixes MX formats build for blackwell

  #2214 opened May 15, 2025

• Re-land the PR of "Add INT8 SDPA path for CPU"

  #2215 opened May 16, 2025

• Convert Pytest to Unittest for tests under test/dtypes/

  #2216 opened May 16, 2025

• Update temp_build.py

  #2218 opened May 17, 2025

2 Issues closed by 2 people

• KleidiAI int4 kernels not loading properly on aarch64 Linux

  #2143 closed May 16, 2025

• New test files will likely fail on ROCM

  #2204 closed May 13, 2025

1 Issue opened by 1 person

• Add MXFP casting kernels from triton Repro

  #2217 opened May 16, 2025

15 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.

• Remove preserve_zero and zero_point_domain from choose_qparams_affine

  #2149 commented on May 17, 2025 • 13 new comments

• [PT2E] Fix per-tensor observer issue with varying shape & rank

  #2177 commented on May 17, 2025 • 9 new comments

• [CPU] Add a new layout for int8_dynamic_activation_int4_weight on CPU

  #2128 commented on May 16, 2025 • 5 new comments

• Enhance test_autoquant_compile to support ROCm

  #2100 commented on May 14, 2025 • 2 new comments

• Eval hf models using lm_eval

  #2179 commented on May 14, 2025 • 1 new comment

• Can FP8 GEMM be enabled via module hooks instead of module swapping?

  #1887 commented on May 12, 2025 • 0 new comments

• Dynamo error with large mesh + AdamWFp8 + bf16 stochastic rounding

  #2074 commented on May 12, 2025 • 0 new comments

• [float8] Add support for blockwise fp8 quantization scheme used in DeepSeek v3

  #1594 commented on May 13, 2025 • 0 new comments

• [QAT] Linear layer's weight quantization granularity can only be per_group

  #2189 commented on May 14, 2025 • 0 new comments

• How does this work with ONNX export and quantization?

  #777 commented on May 14, 2025 • 0 new comments

• [feature request] np.packbits / np.unpackbits, general BitTensors (maybe can be just tensors with dtype torch.bits8 or have a new dtype torch.bits introduced) and bit packed tensors utilities for saving memory / accesses, support for BitTensors wherever BoolTensors are used

  #292 commented on May 15, 2025 • 0 new comments

• [draft] add all_gather_into_tensor

  #1737 commented on May 16, 2025 • 0 new comments

• Fix wrong scale eps applied

  #1770 commented on May 13, 2025 • 0 new comments

• [sparsity] Add PartialLinear module for structured sparsity

  #1982 commented on May 15, 2025 • 0 new comments

• Implement dtensor.shard_dim_alltoall, aten.contiguous, aten.chunk

  #2154 commented on May 13, 2025 • 0 new comments