microsoft/onnxruntime

Pull Requests Commits

Use 2D shapes in MatMulInteger regression tests

bmehta001 committed 33 minutes ago

bb5b207b

Validate K dimension for 1D vector inputs in MatMul to prevent OOB read

bmehta001 committed 1 hour ago

cbbcb33f

[webgpu] house keeping after ORT switch to c++20 (#27904)

fs-eire committed 4 hours ago

Verified 3756e790

Fix CUDA ONNX Attention: min_bias_align crash on SM<80 and MEA NaN for fully-masked batches (#27831)

titaiwangms committed 7 hours ago

Verified eb706ed3

ONNX 1.21.0 integration (#27601)

titaiwangms committed 10 hours ago

Verified aaa49440

[Core] MobileClip Attention Fusion (#27883)

hariharans29 committed 13 hours ago

Verified c9726045

Cleanup: Consolidate `OpKernel::UseSharePrePackedBuffers_V2` and `OpKernel::UseSharePrePackedBuffers` (#27924)

adrianlizarraga committed 14 hours ago

Verified a6592fc0

[WebGPU EP] Support Conv3D (#27917)

edgchen1 committed 14 hours ago

Verified 5b2c0da3

Cleanup for op schema API tests for plugin EPs (#27921)

adrianlizarraga committed 1 day ago

Verified a18e5b98

Add ORT_UNIT_TEST_MAIN_DYNAMIC_PLUGIN_EP_CONFIG_JSON_FILE env var (#27945)

edgchen1 committed 1 day ago

Verified 445dcff7

Fix CPU Attention overflow issue (#27822)

edgchen1 committed 1 day ago

Verified 2bf09e93

[DML EP] Disable 4-D MVN tests for DirectML (#27930)

hariharans29 committed 1 day ago

Verified 32d32b01

Fix typo in CApiTest.VersionConsistencyWithApiVersion. (#27902)

edgchen1 committed 2 days ago

Verified a883c871

webgpu lpnorm support (#27876)

guschmue committed 2 days ago

Verified 768a9375

Fix CPU LRN int overflow issues (#27886)

edgchen1 committed 2 days ago

Verified 5eb29e7d

[MLAS] Add depthwise with multiplier conv special kernel for NCHW data layout on Avx512 (#27874)

hariharans29 committed 3 days ago

Verified 57b265ee

Plugin EP event profiling APIs (#27649)

adrianlizarraga committed 3 days ago

Verified bec27925

[VitisAI] external_ep_library typo fix (#27647)

akholodnamdcom committed 3 days ago

Verified a997c4fd

S390x test fixes (#27404)

AlekseiNikiforovIBM committed 3 days ago

Verified f2c28e2c

[QNN-EP] Fix use-after-free of logger object (#27804)

qc-tbhardwa committed 3 days ago

Verified 0f43e161

webgpu: Optimize DP4A SmallM MatMulNBits tiling (#27910)

qjia7 committed 3 days ago

Verified f22e3a99

[Plugin EP] Add plugin EP APIs to retrieve ONNX operator schemas (#27713)

adrianlizarraga committed 3 days ago

Verified 048e7dc6

[CI] fix: missing `branch` specifier in `schedule` directive (#27914)

sanaa-hamel-microsoft committed 3 days ago

Verified e43d3064

CUDA Plugin EP: Core Implementation (#27816)

tianleiwu committed 3 days ago

Verified 879f6591

[Plugin EP] Add plugin EP Sync API (#27538)

chilo-ms committed 3 days ago

Verified ccd9a5c0

[CI] chore: bump `actions/cache@v5` (#27866)

sanaa-hamel-microsoft committed 3 days ago

Verified cd120ee7

Fix run-level profiling for subgraph operators (#27870)

adrianlizarraga committed 4 days ago

Verified 318a2516

webgpu: Increase MatMulNBits K-parallelism with tile_size_k_vec=32 (#27834)

qjia7 committed 4 days ago

Verified 358628a8

Add per-session thread pool work callbacks API (#27253)

sdotpeng committed 4 days ago

Verified f869122a

Fix integer modulo by zero crash in CPU EP Mod operator (#27833)

Copilot committed 4 days ago

Verified 2cdf0108

Older