microsoft/onnxruntime

Pull Requests Commits

add back onnxruntime_BUILD_DAWN_SHARED_LIBRARY=ON, use --test_parallel 1.

edgchen1 committed 30 days ago

524f45a1

edgchen1 committed 30 days ago

fab822cd

remove unnecessary cmake defines

edgchen1 committed 30 days ago

e2e6c60b

Merge remote-tracking branch 'origin/main' into edgchen1/fix_webgpu_nightly_test

edgchen1 committed 30 days ago

5326be9c

Fix broken link to ONNX Runtime technical reference docs (#33030)

Zapakio6 committed 30 days ago

Verified 397657de

[CUDA] Fix GQA build regression after eligibility/workspace integration (#33179)

chilo-ms committed 30 days ago

Verified 05517e12

Update Android minimal binary size baseline (#33164)

xadupre committed 30 days ago

Verified 3d9d664a

[CUDA] Plumb GQA workspace KV-length envelope knob into the L1 estimator (reader-only) (#33014)

chilo-ms committed 30 days ago

Verified f83bf57d

[CUDA] Consolidate GQA scratch sizing (MEA, unfused, XQA, Flash) into shared workspace recipes (#32945)

chilo-ms committed 30 days ago

Verified e3f71e01

[CUDA] Extract GQA seq-free route eligibility into shared helpers (#33001)

chilo-ms committed 30 days ago

Verified ec82e2a3

[CUDA] Suppress CUDA 13 MSVC build warnings (#33149)

tianleiwu committed 30 days ago

Verified 0eb8a047

rename pipeline

edgchen1 committed 30 days ago

b7f93456

Add ADO nightly pipeline for WebGPU shader validation

edgchen1 committed 30 days ago

f7cda7be

Fix dead links in docs and CONTRIBUTING (#32880)

pratikgx committed 30 days ago

Verified 9a7c1939

Validate ORT format input argument counts (#32865)

danielsongmicrosoft committed 30 days ago

Verified 958927fb

Account for string payloads in initializer size limits (#32867)

danielsongmicrosoft committed 30 days ago

Verified 0d427f8c

Handle missing ConstantOfShape value during float16 conversion (#33089)

Copilot committed 30 days ago

Verified ae245d03

Fix ReshapeFusion crash when fused Reshape's shape input is node-produced (#33091)

anubhavagr committed 30 days ago

Verified 5652d3fa

fix(quantization): avoid intermediate overflow when calculating quantization ranges (#33104)

galleonli committed 30 days ago

Verified b40377d9

Optimize CPU BatchNormalization for NC inputs (#33113)

artyomrabosh committed 30 days ago

Verified 8478e365

Bump sharp from 0.35.4 to 0.35.5 in /js/web/test/e2e/exports/testcases/nextjs-default (#33138)

dependabot[bot] committed 30 days ago

Verified 43c6f17e

Fix Windows clang/no-exceptions portability (#33140)

mustjab committed 31 days ago

Verified 84207093

Fix C API tensor element type conversions at ONNX boundaries (#33066)

Copilot committed 31 days ago

Verified 123f0853

Detect Jetson GPUs in Linux DRM device discovery (#32544)

Copilot committed 31 days ago

Verified 60e534a5

Work around certificate regression on Windows (#33142)

eserscor committed 31 days ago

Verified 38dc99fb

Validate CPU kernel registrations at compile time (#29649)

GopalakrishnanN committed 31 days ago

Verified 053d9b06

Split nightly WebGPU build and tests and enable vcpkg caching

edgchen1 committed 31 days ago

8df9ecd0

Validate CUDA GatherND indices bounds in release mode (#31646)

apsonawane committed 31 days ago

Verified ec1add89

[WebGPU] Cache sparse indexer QSA visibility and scores (#33017)

sayanshaw24 committed 31 days ago

Verified 98468bff

Remove capture of static dump_mutex.

edgchen1 committed 31 days ago

d31e614a

Older