microsoft/onnxruntime

Pull Requests Commits

[OVEP] Update openvino version to 2025.4.1 (#26943)

preetha-intel committed 26 days ago

Verified a14231a5

[QNN EP] Update tensor naming logic in DebugNodeInputsOutputs (#26660)

yuhuchua-qti committed 26 days ago

Verified 3924b6e8

[ICM CXX] Address Pad kernel shortcomings (#26864)

yuslepukhin committed 26 days ago

Verified 5d596088

[webgpu] Simplify the signature of CanApplyFlashAttention (#26926)

qjia7 committed 27 days ago

Verified 56c984ff

[webgpu] Support `Split-K` in more situations (#26806)

Jiawei-Shao committed 27 days ago

Verified 4a858a82

[CUDA] Speed up flash attention build (#26924)

tianleiwu committed 27 days ago

Verified 541d5daf

GPG changed default install location on 12/31/2025 for Windows (#26917)

eserscor committed 27 days ago

Verified 751af64a

[QNN EP] Fix the build error when the specified QNN library is missing (#26872)

kuanyul-qti committed 28 days ago

Verified 517e06c6

[EP ABI] Add OrtKernelInfo APIs for kernel-based plugin EPs (#26803)

adrianlizarraga committed 28 days ago

Verified 27e6002d

[QNN EP] Add Static bias encoding support for Conv op (#26710)

quic-ashwshan committed 28 days ago

Verified 1e393751

Bump qs and body-parser in /onnxruntime/test/wasm (#26914)

dependabot[bot] committed 29 days ago

Verified 342f7193

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

baijumeswani committed 29 days ago

Verified 0409ba6f

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

qjia7 committed 29 days ago

Verified 34a0b152

[webgpu] Optimize AttentionPrepare (#26850)

qjia7 committed 29 days ago

Verified 5bc10a39

[webgpu] Add ScatterElements support (#26903)

qjia7 committed 29 days ago

Verified 63b5cefc

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

quic-boyuc committed 29 days ago

Verified 25733463

Update VCPKG to 25.08.27 (#26839)

eserscor committed 29 days ago

Verified 39b997e9

Update TRT to 10.14 (#26871)

eserscor committed 29 days ago

Verified bde08309

Update GQA benchmark to support bfloat16 (#26898)

tianleiwu committed 29 days ago

Verified 5307dc59

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

edgchen1 committed 29 days ago

Verified db3eb22c

Generalize noop_with_empty_axes handling across all Reduce operators (#26436)

naomiOvad committed 30 days ago

Verified 838b17a3

Reduce GQA cpu test combinations (#26897)

tianleiwu committed 32 days ago

Verified ecf164a9

Fix C++ documentation generation (#26901)

adrianlizarraga committed 32 days ago

Verified 0d59f8d9

Enable BF16 Cutlass FMHA (#26894)

tianleiwu committed 32 days ago

Verified d1857d12

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

adrianlizarraga committed 32 days ago

Verified 07ec4515

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

dependabot[bot] committed 33 days ago

Verified 8bd5b739

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

fs-eire committed 35 days ago

Verified 94e7a1c6

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

tianleiwu committed 35 days ago

Verified 7ad0de5b

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

vishalpandya1990 committed 35 days ago

Verified 1a112a28

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

qjia7 committed 36 days ago

Verified aab56616

Newer Older