All pull requests

Pull requests

• Give backends the method's metadata at init

  CLA Signedmeta-exported
  #24220·sivapatibandla opened Oct 28, 2026·

  ·
  4

• Skip xnn_reshape_runtime when the input shapes have not changed (#24219)

  CLA Signedmeta-exported
  #24219·billmguo opened Oct 27, 2026Contributor·

  ·
  3

• Support torch.empty_like when lowering to Edge, and speed up GroupBasedPartitioner

  CLA Signedrelease notes: exir
  #24218·shoumikhin opened Oct 27, 2026Contributor·

  ·
  5

• Build operator lookup names without snprintf

  CLA Signed
  #24217·rascani opened Oct 27, 2026Contributor·

  ·
  2

• Use minimal PAL and nano libraries in Cortex-M size tests

  CLA Signed
  #24216·rascani opened Oct 27, 2026Contributor·

  ·
  3

• Drop the "newer than 2.15" marks from the TensorRT backend page

  CLA Signedrelease notes: docs
  #24214·shoumikhin opened Oct 27, 2026Contributor·

  ·
  4

• Pin OpenVINO CI to the 2026.4.1 release instead of a deleted nightly

  CLA Signed
  #24212·pytorchbot opened Oct 27, 2026Collaborator·

  ·
  1

• Update the TensorRT backend docs page

  CLA Signed
  #24211·pytorchbot opened Oct 27, 2026Collaborator·

  ·
  1

• Fix device placement of constants, shared inputs and delegate outputs

  CLA Signed
  #24210·pytorchbot opened Oct 27, 2026Collaborator·

  ·
  1

• [PyBindings] Torch-free follow-ups: reused inputs, error reasons, bfloat16 shape, dtype names, tests, docs

  CLA Signed
  #24209·pytorchbot opened Oct 27, 2026Collaborator·

  ·
  1

• Serialize only a view constant's own bytes in XNNPACK and Vulkan

  CLA Signedmodule: vulkan
  #24208·pytorchbot opened Oct 27, 2026Collaborator·

  ·
  1

• Let a backend share one delegate across calls of the same lowered module

  CLA Signed
  #24207·pytorchbot opened Oct 27, 2026Collaborator·

  ·
  1

• Stop installing test-only packages with the executorch package

  CLA Signed
  #24206·pytorchbot opened Oct 27, 2026Collaborator·

  ·
  1

• Qualcomm AI Engine Direct - Add QNN/HTP joint-graph training toy example

  release notes: qualcomm
  #24205·likhitanavali opened Oct 27, 2026·

  ·
  4

• Multi-method delegate: share weights across N command streams

  ciflow/trunkCLA Signedmeta-exportedmodule: arm
  #24204·3l1 opened Oct 27, 2026Contributor·

  ·
  3

• Enforce per-dim upper bounds for DYNAMIC_BOUND inputs in set_input

  CLA Signedcommunity: contributionmodule: runtimerelease notes: runtime
  #24203·AxelNoun opened Oct 27, 2026Contributor·

  ·
  1

  

• Raise InternalError for non-CPU constant storage in the emitter

  CLA Signedcommunity: contributionmodule: cudamodule: exir
  #24202·AxelNoun opened Oct 27, 2026Contributor·

  ·
  1

  2

  

• Arm backend: Decompose gated DeltaNet for TOSA delegation

  ciflow/trunkCLA Signedmodule: armrelease notes: arm
  #24201·xingguo01 opened Oct 27, 2026Collaborator·

  ·
  1

• Add skill for arm backend development

  CLA Signedpartner: armrelease notes: none
  #24200·AdrianLundell opened Oct 27, 2026Collaborator·

  ·
  1

• [RELEASE ONLY CHANGES] Prepare ExecuTorch 1.6 release dependencies

  ciflow/dockerCLA Signed
  #24199·JacobSzwejbka opened Oct 27, 2026Contributor·

  ·
  1

• [RELEASE ONLY CHANGES] Update documentation for ExecuTorch 1.6

  CLA Signed
  #24198·JacobSzwejbka opened Oct 27, 2026Contributor·

  ·
  1

• [RELEASE ONLY CHANGES] Pin 1.6 CI to test-infra release/2.15

  ciflow/dockerCLA Signed
  #24197·JacobSzwejbka opened Oct 27, 2026Contributor·

  ·
  1

• Accept empty tensor bindings in CPUBackend execute (#24195)

  CLA Signedmeta-exported
  #24195·JakeStevens opened Oct 27, 2026Contributor·

  ·
  3

• [ET-VK][SDPA] Preserve shared KV cache semantics

  CLA Signed
  #24188·SS-JIA opened Oct 27, 2026Contributor·

  ·
  1

• [ET-VK][embedding] Support per-row Q4 scales

  CLA Signed
  #24187·SS-JIA opened Oct 27, 2026Contributor·

  ·
  2