microsoft/onnxruntime

Pull Requests Commits

Merge remote-tracking branch 'origin/main' into edgchen1/cpp20_fix

edgchen1 committed 5 days ago

270f4119

Doc fixes (#27228)

edgchen1 committed 5 days ago

Verified 735e69a3

Remove AzurePowerShell pwsh parameter in tools/ci_build/github/azure-pipelines/templates/publish-symbolrequestprod-api.yml (#27339)

edgchen1 committed 5 days ago

Verified 301aaf54

Add boundary checks and add tests for SparseTensorProtoToDenseTensorProto (#27323)

yuslepukhin committed 5 days ago

Verified 1ade88ab

mlas/arm64: add NEON conv asm kernels and tune NCHWC kernel selection (#27099)

milpuz01 committed 5 days ago

Verified bd8f781f

Update ORT_API_VERSION (#27280)

edgchen1 committed 5 days ago

Verified 0c2502c7

BaseTester: support plugin EPs with compiled nodes and registered kernels (#27176)

adrianlizarraga committed 6 days ago

Verified b3a34bb2

Fix NuGet DLL Loading on Linux and macOS (#27266)

tianleiwu committed 6 days ago

Verified 1a71a5f4

Fix CUDA minimal build requiring CUDNN_HOME (#27308)

ingyukoh committed 6 days ago

Verified d7f32e25

[CUDA] Fix build errors (#27319)

tianleiwu committed 6 days ago

Verified 30968e9e

Fix ConfigEps execution provider ordering in test files (#27014)

fs-eire committed 6 days ago

Verified a9ebcbd5

Update Microsoft.ML.OnnxRuntime.Foundry Package (#27294)

baijumeswani committed 7 days ago

Verified 26cc7ce9

Sync optimizer opset versions with CPU kernel registrations (#27270)

Copilot committed 7 days ago

Verified a70ac2f6

Check NodeArg has name in ORT formal model load (#27297)

skottmckay committed 7 days ago

Verified 99a46e01

Fix WebGPU Conv auto_pad=SAME_UPPER padding calculation (#27249)

ingyukoh committed 7 days ago

Verified 8ffc33c6

win arm64 python packages (#27299)

eserscor committed 7 days ago

Verified b440277c

Speed up iOS/macOS CocoaPods packaging pipeline (#27279)

edgchen1 committed 7 days ago

Verified 5a9d721d

Improve encapsulation of weight_data_type_freq_ (#27292)

ashrit-ms committed 7 days ago

Verified 765b1801

[CUDA] GroupQueryAttention with XQA and Quantized KV Cache Support (#27246)

tianleiwu committed 7 days ago

Verified 9adf238e

[onnxruntime_perf_test] Fix Mac peak working set size value (#27302)

edgchen1 committed 7 days ago

Verified 2cf5bbde

Support group query attention in Attention(23) CUDA (#27082)

Copilot committed 7 days ago

Verified 5a9877a0

[Build] Fix java macos (#27271)

tianleiwu committed 7 days ago

Verified 16667b10

[Build] Adjust nvcc_threads for CI (#27296)

tianleiwu committed 7 days ago

Verified 4295524c

[MLAS] Fix Lut GEMM Flakiness and Accuracy (#27216)

tianleiwu committed 7 days ago

Verified 9a4f4632

[Shape Inference] Fix GQA shape inference for present outputs (#27250)

Honry committed 8 days ago

Verified 0a478c0d

[CI] Build NCHWc code on Windows/Linux ARM64 CIs (#27273)

hariharans29 committed 9 days ago

Verified b214734c

Improve WebGPU MatMulNBits to support zero pointer for 2bits (#27285)

HectorSVC committed 9 days ago

Verified 40d36b19

Add Contributor Compilation Tool for Release Notes (#27284)

tianleiwu committed 9 days ago

Verified bcd56051

Revert "DEBUG: CMake generate tracing"

edgchen1 committed 9 days ago

2ef0bdbf

try disabling module scan for Android QNN

edgchen1 committed 9 days ago

79de47aa

Older