All pull requests

Pull requests

• Reject overflowing Concat axis dimensions

  #33235·Xavier Dupré (xadupre) opened Oct 9, 2026Member·

  ·
  3

• Remove stale Intel MKL third-party notice

  #33233·Xavier Dupré (xadupre) opened Oct 9, 2026Member·

  ·
  1

  1

• [WebGPU] Prepack ConvTranspose1D/2D initializer weights

  #33231·Yang Gu (gyagp) opened Oct 9, 2026Contributor·

  ·
  2

• [CUDA][WebGPU] Add PackedSparseAttentionIndexerMerge for MTP index sharing

  #33224·kunal-vaishnavi opened Oct 9, 2026Contributor·

  ·

• [React Native] Add opt-in encrypted compiled EPContext device workflow

  #33222·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  5

• [Objective-C] Add encrypted compiled EPContext inference coverage

  #33223·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  7

• Test Java encrypted compiled-model inference

  #33217·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  11

• Test Python encrypted compiled-model inference

  #33218·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  9

• Test C# encrypted compiled-model inference

  #33221·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  5

• Test Rust encrypted compiled-model inference

  #33220·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  5

• Test Node.js encrypted compiled-model inference

  #33219·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  2

• Add executable EPContext fixture for encrypted binding tests

  #33216·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  9

• Bump plugin ep versions

  #33214·Tianlei Wu (tianleiwu) opened Oct 8, 2026Contributor·

  ·
  1

• [WebGPU] Add GatedDeltaNetStateReplay contrib operator

  #33213·aciddelgado opened Oct 8, 2026Contributor·

  ·
  1

• [WebGPU EP] fuse layer norm projections into gated delta net

  #33211·Prathik Rao (prathikr) opened Oct 8, 2026Contributor·

  ·
  2

• Update libprotobuf-mutator to handle protobuf api changes

  #33210·eserscor opened Oct 8, 2026Contributor·

  ·
  3

• Make CPUinfo DLL-unload ownership checks deterministic

  #33205·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  1

• Finish React Native workers before publishing promise results

  #33204·Gopalakrishnan Nallasamy (GopalakrishnanN) opened Oct 8, 2026Contributor·

  ·
  1

  3

• [WebGPU] Skip unsupported FP16 execution in operator tests

  #33201·Yang Gu (gyagp) opened Oct 8, 2026Contributor·

  ·
  4

• Enable 1DS telemetry in exception-free builds

  #33199·bmehta001 opened Oct 8, 2026Contributor·

  ·
  5

  

• Fix Windows float16 model-path conversion

  #33193·A Aswanth Raj (aswanth-07) opened Oct 8, 2026·

  ·
  3

• Improve INT4 decode and GEMM profiler buffer safety

  #33177·Sunghoon Choi (hanbitmyths) opened Oct 7, 2026Collaborator·

  ·
  21

• Add FP16 and BF16 H512 GQA decode support

  #33176·Sunghoon Choi (hanbitmyths) opened Oct 7, 2026Collaborator·

  ·
  14

• Guard normalized WebGPU GEMM dispatch bounds

  #33174·danielsongmicrosoft opened Oct 7, 2026Contributor·

  ·
  4

• cuda plugin: add native sm_120 SASS to the LLM target under MSVC

  #33173·Tianlei Wu (tianleiwu) opened Oct 7, 2026Contributor·

  ·
  2