microsoft/onnxruntime

Pull Requests Commits

align with latest API naming

fs-eire committed 15 days ago

74b2ed44

header-only adapter for EP API

fs-eire committed 24 days ago

884d63bd

Build onnxruntime with `caller-framework WinAI` for FoundryLocal (#26915)

baijumeswani committed 24 days ago

Verified 0409ba6f

[webgpu] Support any batch size for dp4a matmul path (#26884)

qjia7 committed 24 days ago

Verified 34a0b152

[webgpu] Optimize AttentionPrepare (#26850)

qjia7 committed 24 days ago

Verified 5bc10a39

[webgpu] Add ScatterElements support (#26903)

qjia7 committed 24 days ago

Verified 63b5cefc

[QNN EP] Implement Platform-Aware UT Skipping Infra for QNN (#26728)

quic-boyuc committed 24 days ago

Verified 25733463

Update VCPKG to 25.08.27 (#26839)

eserscor committed 24 days ago

Verified 39b997e9

Update TRT to 10.14 (#26871)

eserscor committed 24 days ago

Verified bde08309

Update GQA benchmark to support bfloat16 (#26898)

tianleiwu committed 24 days ago

Verified 5307dc59

Plugin EP API - Add OrtEp::IsConcurrentRunSupported (#26859)

edgchen1 committed 24 days ago

Verified db3eb22c

Generalize noop_with_empty_axes handling across all Reduce operators (#26436)

naomiOvad committed 25 days ago

Verified 838b17a3

Reduce GQA cpu test combinations (#26897)

tianleiwu committed 27 days ago

Verified ecf164a9

Fix C++ documentation generation (#26901)

adrianlizarraga committed 27 days ago

Verified 0d59f8d9

Enable BF16 Cutlass FMHA (#26894)

tianleiwu committed 27 days ago

Verified d1857d12

[CXX API] Fix memory leak for KernelContext_GetAllocator (#26883)

adrianlizarraga committed 27 days ago

Verified 07ec4515

Bump qs and body-parser in /js/web (#26888)

dependabot[bot] committed 28 days ago

Verified 8bd5b739

Initial change to enable WebGPU EP to suport plugin API (#25705)

fs-eire committed 30 days ago

Verified 94e7a1c6

Fix DoS vulnerability in FuseReluClip: handle empty tensor (#26878)

tianleiwu committed 30 days ago

Verified 7ad0de5b

Add blackwell check in TRTRTX EP unit tests for FP4/FP8 Custom ops (#26832)

vishalpandya1990 committed 30 days ago

Verified 1a112a28

[webgpu] Fix errors found by matmul2bits tests (#26880)

qjia7 committed 31 days ago

Verified aab56616

[webgpu] make PIX frame generator per session (#26873)

fs-eire committed 31 days ago

Verified 8158d4ed

Do not run auditwheel on QNN whls (#26837)

eserscor committed 31 days ago

Verified 7b9de5b4

[webgpu] refactor initialization of WebGPU Context params (#26855)

fs-eire committed 32 days ago

Verified 2f0eb77b

WebGPU: Use dedicated prepack allocator for kernel prepacking (#26857)

jchen10 committed 34 days ago

Verified 38355ba0

[EP ABI] Add weight pre-packing support to kernel-based plugin EPs (#26754)

adrianlizarraga committed 34 days ago

Verified 2d1ed5b7

Proposed changes to model compilation telemetry (#26804)

adrastogi committed 37 days ago

Verified 573d395d

Add Visual Studio 2026 CMake generator support (#26802)

Copilot committed 38 days ago

Verified ed89ce7c

fix crash in webgpu init when OrtEnv is re-created (#26836)

guschmue committed 38 days ago

Verified 7b5a93ef

[WebGPU] Fix Conv prepacking mismatch with Im2ColMatMul path detection (#26833)

jchen10 committed 39 days ago

Verified 49002015

Older