microsoft/onnxruntime

Pull Requests Commits

Merge branch 'main' into Cjian/conv-int-u8s8

jchen351 committed 302 days ago

da74b9fc

Limit the Pipeline ability to build cuda 11 (#24073)

jchen351 committed 302 days ago

Verified a8fb7868

Change type len from int to size_t (#24157)

jiafatom committed 302 days ago

Verified a4b8f11c

Proper Error Message when fp16 model is used for Beam Search in CPU (#24151)

tianleiwu committed 303 days ago

Verified de502c89

Upgrade Big Model pipeline CUDA from 11.8 to 12.x (#24156)

tianleiwu committed 303 days ago

Verified bb005b93

[Native WebGPU] Add Matmul (#24046)

vraspar committed 303 days ago

Verified ce65e253

add cache "onnxnodetests" for node tests (#24150)

fs-eire committed 303 days ago

Verified afaf4a5e

[js] Add API for accessing metadata of a model's input/output (#23937)

fs-eire committed 303 days ago

Verified 618aef7e

[js/web] allow bundler import condition for not bundling wasm (#24014)

fs-eire committed 303 days ago

Verified 78d91cdd

[webgpu] add option to perserve device and enable in unittest (#24115)

fs-eire committed 303 days ago

Verified e03631ee

Address Windows CUDA build issue (#24149)

yuslepukhin committed 303 days ago

Verified 5244d68b

refactor mac CI pipelines (#24138)

fs-eire committed 303 days ago

Verified 373b9e2a

[CPU] Add fp16 support to sparse attention (#24015)

fajin-corp committed 303 days ago

Verified 828e3726

[mobile] Add Android NuGet BrowserStack test to NuGet packaging pipeline (#23580)

carzh committed 303 days ago

Verified 8eb8c2b0

[Shape Inference] Add shape inference for QLinearAdd and QLinearMul ops (#24090)

pravg-amd committed 303 days ago

Verified 2b5c9da6

Bump next from 15.1.2 to 15.2.3 in /js/web/test/e2e/exports/testcases/nextjs-default (#24132)

dependabot[bot] committed 304 days ago

Verified 5ed900e9

Fix attention QK linkage error (#24134)

kunal-vaishnavi committed 304 days ago

Verified 2b3d7fb1

Update package.json to make the dist avaliable again (#23991)

jchen351 committed 304 days ago

Verified 3012d445

Update T5 Onnx Export and Optimization (#23949)

tianleiwu committed 305 days ago

Verified d84314cb

Deleted the constant SKIP_CUDA_TEST_WITH_DML (#24113)

CodingSeaotter committed 306 days ago

Verified 4959468a

Refactor Webnn IsSupported*() to use constant initializers. (#24118)

yuslepukhin committed 306 days ago

Verified cd9406bf

add test cases for webgpu ep in web (#24117)

fs-eire committed 306 days ago

Verified 0a363d9e

Integrate KleidiAI for MatMulNBits via MlasQNBitGemm (#23627)

MichaelTylerArm committed 306 days ago

Verified 90c5ffb5

skip MOE python test when MPI is not installed (#24116)

tianleiwu committed 307 days ago

Verified dcc1f5ac

[webgpu EP] put GetMaxComponents and SumVector to one place. (#24122)

fs-eire committed 307 days ago

Verified 9e53afab

[webgpu]Add MaxPool and AveragePool (#23714)

jchen10 committed 307 days ago

Verified 7a6514c8

[OpenVINO]Session Options Appended After AppendExecutionProvider (#23852)

sfatimar committed 307 days ago

Verified 49024a1e

[JSEP] handles edge case in gridsample operator (#24121)

prathikr committed 307 days ago

Verified 469fb7e3

[MIGraphX EP] check POLICY CMP0144 availability before used (#24104)

apwojcik committed 307 days ago

Verified 9922d480

[MIGraphX EP] rename HIPPinnedAllocator to MIGraphXPinnedAllocator (#24103)

apwojcik committed 307 days ago

Verified 16b0b323

Older