microsoft/onnxruntime

Pull Requests Commits

[Test] End profiling after 10 runs

qjia7 committed 163 days ago

5ac43f24

[webgpu] Register GQA based on graph capture (#26384)

qjia7 committed 164 days ago

Verified f7fd3b52

Bump actions/upload-artifact from 4 to 5 (#26411)

dependabot[bot] committed 164 days ago

Verified 3a6a4c2a

Bump actions/download-artifact from 5 to 6 (#26409)

dependabot[bot] committed 164 days ago

Verified 3862fe54

[WebGPU] add unidirectional support for MHA (#26071)

fs-eire committed 164 days ago

Verified 41429ed9

[CPU] Use MayInPlace kernel def hint for FusedConv kernel (#26422)

hariharans29 committed 164 days ago

Verified d85627ae

Fix iOS packaging pipeline (#26426)

edgchen1 committed 164 days ago

Verified 0f6cffc1

use std::move(model_proto) to avoid extra copy (#26372)

mingyueliuh committed 165 days ago

Verified 852f0902

[js] Upgrade ESLint from v8 to v9 for subfolder /js/ (#26419)

fs-eire committed 165 days ago

Verified c6c6d784

[CUDA] Add nightly gpu package and publish pipelines for CUDA 13 (#26420)

tianleiwu committed 165 days ago

Verified 16332991

Update ORT_API_VERSION to 24 (#26418)

adrianlizarraga committed 165 days ago

Verified e8b054ca

[Web] Add wasm and mjs files to package.json exports to improve bundler support (#26394)

KingSora committed 165 days ago

Verified 06004826

[webgpu] Fused GeneratePositionIDs into FusedQKRotaryEmbedding (#26400)

xiaofeihan1 committed 166 days ago

Verified 771a4d49

[WebGPU] allow async shader compilation (#25941)

fs-eire committed 166 days ago

Verified 954bb7bc

Upgrade cpuinfo (#26405)

Changming Sun committed 166 days ago

Verified 6e19cbde

Make onnxruntime_benchmark run (#26404)

yuslepukhin committed 166 days ago

Verified fdaf8b64

[NV TRT RTX EP] Package CUDA Runtime and TRT RTX with NV TensorRT RTX EP python wheel (#26115)

keshavv27 committed 166 days ago

Verified 5568c3af

Disable build flatc for tvOS or visionOS (#26380)

hans00 committed 166 days ago

Verified 0463aa9f

Add LSX support for S8S8 and S8U8 GEMM kernels (#24397)

wszqkzqk committed 166 days ago

Verified 8267066d

[CANN] Fix the ACL_ERROR_REPEAT_INITIALIZE error that occurs when coexisting… (#26193)

bachelor-dou committed 168 days ago

Verified f20df72d

Add CreateQuantPybindModule into orttraining (#26401)

jiafatom committed 168 days ago

Verified 697283dd

[MLAS] Fix rotary avx2 kernel invalid access (#26389)

tianleiwu committed 168 days ago

Verified 1f458385

Fix for micro benchmark build failure with c++20 (#26299)

JonathanC-ARM committed 168 days ago

Verified 6e676641

FP16 inference performance improvement on CPU (#25680)

nikhilfujitsu committed 168 days ago

Verified 42869cac

[webgpu] Use DoTranspose directly in Conv Op (#26074)

wenqinI committed 170 days ago

Verified b3ba5803

[webgpu] Remove 'webgpu' suffix from filenames (#26287)

daijh committed 170 days ago

Verified cd3aa49d

[webgpu] Fix graph capture broken (#26383)

qjia7 committed 171 days ago

Verified 949c0de7

Bump parkerbxyz/suggest-changes from 2 to 3 (#25839)

dependabot[bot] committed 171 days ago

Verified c7dfc25d

Bump vite from 6.3.6 to 6.4.1 in /js/web/test/e2e/exports/testcases/vite-default (#26370)

dependabot[bot] committed 171 days ago

Verified e7ef489d

[webgpu] Expand Squeeze version to 24 (#26359)

qjia7 committed 171 days ago

Verified b6b90a08

Older