All pull requests

Pull requests

• fix(build): accept ARM64 hosts in qualcomm pybind gate and custom_ops checks

  release notes: build
  #24835·SaidSultani opened Nov 10, 2026·

  ·
  4

• xplat/executorch/export/tests

  CLA Signedmeta-exported
  #24834·meta-codesync[bot] opened Nov 10, 2026Bot·

  ·
  2

• Arm backend: Add Clang bare-metal toolchain

  ciflow/trunkCLA Signedmodule: armpartner: armrelease notes: arm
  #24831·perheld opened Nov 10, 2026Collaborator·

  ·
  3

• Qualcomm AI Engine Direct - HF API sample script

  CLA Signed
  #24830·winskuo-quic opened Nov 10, 2026Contributor·

  ·
  2

• [RFC] Qualcomm AI Engine Direct - [VLA] Lerobot-ExecuTorch simulation framework

  CLA Signed
  #24829·DannyYuyang-quic opened Nov 10, 2026Contributor·

  ·
  5

• Fix issue for changing transformer version

  CLA Signed
  #24828·Jiseong-oh opened Nov 10, 2026Collaborator·

  ·
  2

• Make aoti_torch__reinterpret_tensor offset relative to self

  CLA Signedmeta-exported
  #24827·Gasoonjia opened Nov 10, 2026Contributor·

  ·
  5

• Fix optimized add with alpha when the first operand has one element

  CLA Signed
  #24826·luciusacarr opened Nov 10, 2026·

  ·
  2

• Load AOTI plugins into hosts that don't share their C++ runtime

  CLA Signedmeta-exported
  #24818·mattiasbrand opened Nov 9, 2026·

  ·
  3

• Build the CUDA backend outside fbcode, with the LLM cache optional

  CLA Signedmeta-exported
  #24817·mattiasbrand opened Nov 9, 2026·

  ·
  6

• Preserve an empty selective primitive-operator set (#24815)

  CLA Signedmeta-exported
  #24815·ivayloen opened Nov 9, 2026Contributor·

  ·
  3

• [XNNPACK] Reject addmm with non-default alpha or beta

  CLA Signedrelease notes: xnnpack
  #24814·JakeStevens opened Nov 9, 2026Contributor·

  ·
  3

• Add Phonon (Gradium 31M TTS) example with multi-backend export

  CLA Signedmeta-exported
  #24810·psiddh opened Nov 9, 2026Contributor·

  ·
  5

• Swap reverse-broadcast operands once in handle_broadcast_elementwise

  CLA Signed
  #24809·JakeStevens opened Nov 9, 2026Contributor·

  ·
  2

• Break the exir backend_api <-> program import cycle

  CLA Signed
  #24802·JakeStevens opened Nov 9, 2026Contributor·

  ·
  4

• [runtime] Fix null operator overload logging and named data key dereferences

  CLA Signedcommunity: contributionrelease notes: runtime
  #24801·AhmadHassan-BTed opened Nov 9, 2026·

  ·
  1

  6

• Add an aten.elu kernel and a single-kernel aten.silu

  CLA Signedmeta-exported
  #24800·psiddh opened Nov 9, 2026Contributor·

  ·
  4

• OpenVINO: transpose channels-last tensors at partition edges

  CLA Signed
  #24797·suryasidd opened Nov 9, 2026Collaborator·

  ·
  13

• Arm backend: Add shared device to VGF backend.

  ciflow/trunkCLA Signedmodule: armrelease notes: arm
  #24795·wwwind opened Nov 9, 2026Collaborator·

  ·
  1

• Add the aoti_torch_cuda_nonzero fallback shim (#24787)

  CLA Signedmeta-exported
  #24787·Gasoonjia opened Nov 9, 2026Contributor·

  ·
  5

• [OpenVINO] Import the partitioner without needing nncf

  CLA Signedcommunity: contribution
  #24785·sohailshk opened Nov 9, 2026·

  ·
  6

• [XNNPACK] Skip linear conversion when the weight transpose was folded

  CLA Signedcommunity: contribution
  #24784·sohailshk opened Nov 9, 2026·

  ·
  1

  5

• CUDA backend: create the temporary kernel library file safely

  CLA Signedmodule: cudarelease notes: backends
  #24783·shoumikhin opened Nov 9, 2026Contributor·

  ·
  17

• Metal backend: free only the destroyed delegate's memory

  CLA Signedcommunity: contribution
  #24782·abdelaziz-mahdy opened Nov 8, 2026Contributor·

  ·
  10

• [ET-WebGPU] Keep fp16 elementwise ops on CPU

  CLA Signedcommunity: contribution
  #24781·abdelaziz-mahdy opened Nov 8, 2026Contributor·

  ·
  3