Commits microsoft/onnxruntime

Bump tmp from 0.2.5 to 0.2.7 in /js/web (#28694)

dependabot[bot] committed 166 days ago

Verified a9cfc478

Bump tmp from 0.2.4 to 0.2.6 in /onnxruntime/test/wasm (#28683)

dependabot[bot] committed 166 days ago

Verified 9baa33a2

Bump qs and body-parser in /onnxruntime/test/wasm (#28644)

dependabot[bot] committed 166 days ago

Verified 615d0d79

Fix CPU QLinearConv: support per-channel weight zero points with distinct values (#28456)

Copilot committed 167 days ago

Verified 13af6597

Build onnxruntime with training, training_apis, tests and gcc-15 (#27191)

AlekseiNikiforovIBM committed 169 days ago

Verified 3c7213d6

Update microsoft_gsl from v4.0.0 to v4.2.1 (fixes C4875 deprecation) (#28527)

Copilot committed 169 days ago

Verified 31146515

Introduce checks to prevent buffer overflow, add tests (#28713)

yuslepukhin committed 169 days ago

Verified df44eabd

CUDA Plugin EP: NHWC Cleanup & Hardening (#28612)

tianleiwu committed 169 days ago

Verified d165fba0

Add explicit CUDA version suffix to GPU release artifacts (#28691)

kpkbandi committed 169 days ago

Verified 6a517f55

Update CUDA 12.8 to 13.0 in CI workflows (#28458)

Copilot committed 169 days ago

Verified 97e7b2a7

Add `tools/python/compile_contributors.py` `--paths` option (#28710)

edgchen1 committed 170 days ago

Verified abbc2abc

Flash Attention style tiled computation for CPU GQA quantized KV cache (#28695)

tianleiwu committed 170 days ago

Verified 7e82d19d

Address external path references in loaded models (#28709)

yuslepukhin committed 170 days ago

Verified 77d32c3a

fix(partitioning_utils): include Loop/If/Scan implicit inputs in MetaDef (#28608)

zz002 committed 170 days ago

Verified eefc22f2

fix(quantization): emit axis on DequantizeLinear for per-channel dynamic quantization (#28228)

Rishi-Dave committed 170 days ago

Verified b668e476

Replace direct inclusion of <cub/cub.cuh> with "core/providers/cuda/cu_inc/cub.cuh" wrapper. (#28705)

edgchen1 committed 170 days ago

Verified f1b13052

[WebGPU EP] Add environment variable to dump shader code to a file, move shader key validation to nightly build (#28674)

edgchen1 committed 170 days ago

Verified 4b7f8f17

Address CUDA ReduceL2 negative results and add test coverage (#28681)

yuslepukhin committed 170 days ago

Verified efbffdd2

[WebGPU] QKV and MLP layer fusions for Qwen3-style models (#28280)

hariharans29 committed 170 days ago

Verified 88ca23fc

Update protobuf version to 6.33.5 (#28684)

sushraja-msft committed 170 days ago

Verified 04c900d6

[webgpu] Per-graph buffer manager for WebGPU multi-graph capture (#28260)

qjia7 committed 171 days ago

Verified 5d6cbb67

Update GQA op schema (#28689)

apsonawane committed 171 days ago

Verified 46fdcbba

Use fp32 accumulation in SkipLayerNorm/EmbedLayerNorm CUDA kernels (#28682)

tianleiwu committed 171 days ago

Verified 26871ab4

[WebGPU plugin EP] Enforce minimum ORT version specified by `plugin-ep-webgpu/MIN_ONNXRUNTIME_VERSION` (#28687)

edgchen1 committed 171 days ago

Verified b1880617

Guard removed APIs in TRT 11 (#28611)

kevinch-nv committed 171 days ago

Verified 53fcead6

[CoreML EP] Add Sin and Cos unary ops (#28596)

maxwbuckley committed 171 days ago

Verified 71cfbb0f

Speed up CUDA CI build: split into per-arch OBJECT libraries, add --flash_nvcc_threads, and enable quick build mode (#28645)

tianleiwu committed 171 days ago

Verified b0924f47

Propagate outer scope type info to subgraphs during verification (#27707)

Rishi-Dave committed 172 days ago

Verified bdd52fa1

Fix CUTLASS FMHA BiasLoader alignment for unaligned kernel path (#28369)

justinchuby committed 172 days ago

Verified 1f92c9d8

remove some webgpu ci tasks to speedup ci (#28642)

Guenther Schmuelling committed 172 days ago

Verified a42351e3