microsoft/onnxruntime

Pull Requests Commits

Select CUDA 13 dependencies for Linux GPU NuGet tests

Copilot committed 50 days ago

Verified 1b36be0e

Align downstream GPU package tests with CUDA 13

Copilot committed 50 days ago

Verified e3f5b59e

Default Java GPU packaging to CUDA 13

Copilot committed 50 days ago

Verified 63ae8b19

Copilot committed 50 days ago

Verified 3b11933a

Remove unnecessary spectre patch (#32774)

eserscor committed 50 days ago

Verified 4119cd60

Validate protobuf consistency when ONNX comes from an installed package (#31346)

Copilot committed 50 days ago

Verified f0fd4e2e

[WebGPU] Organize self-contained provider tests (#32729)

gyagp committed 50 days ago

Verified 9228a096

[WebNN EP] Support GroupNormalization, GroupNorm and SkipGroupNorm (#32606)

Honry committed 50 days ago

Verified 65bb482b

[CUDA] Pass Concat per-input metadata by value (#32119)

tianleiwu committed 50 days ago

Verified 8cf10e7b

Add H128 INT8 paged speculative XQA (#32740)

baijumeswani committed 50 days ago

Verified 41426bd5

[CUDA] Bound fpA_intB tactic profiling time for expensive GEMMs (#32758)

tianleiwu committed 50 days ago

Verified 1378d6be

Update Android minimal size baseline (#32772)

jiafatom committed 50 days ago

Verified d7c441f0

Move the WebGPU builds back to a specialized pool (#32765)

eserscor committed 51 days ago

Verified bed64d76

Remove stale foundry local custom nuget packaging pipeline. (#32760)

eserscor committed 51 days ago

Verified 03835c47

Enable CUDA W8 M=8 fast path for an SM121 FP16 shape (#32742)

baijumeswani committed 51 days ago

Verified 26939e1b

Validate AllGather shape attributes (#32554)

apsonawane committed 51 days ago

Verified 7c22865e

Fix CPU MHA shared cache length handling (#32723)

apsonawane committed 51 days ago

Verified 8c98fa14

Fix DML Resize ROI axis expansion (#32747)

apsonawane committed 51 days ago

Verified 535151bd

Validate CUDA FMHA seqstart/seqlen tensor values (#31641)

apsonawane committed 51 days ago

Verified 48fc67b6

Document model loading performance options (#32712)

xadupre committed 51 days ago

Verified 9fc58b13

Fix concurrent XNNPACK allocator initialization (#32489)

SiluPanda committed 51 days ago

Verified 9ac715b4

Fix OOB read in InferenceContextImpl::getInputData (#32681)

bbernhar committed 51 days ago

Verified e5f272c9

[WebGPU] Trim generated WGSL source-reference whitespace (#32736)

gyagp committed 51 days ago

Verified 292a2aaf

Reject duplicate model-local functions (#32750)

apsonawane committed 51 days ago

Verified 9b25e505

Validate ORT format string initializers (#32751)

apsonawane committed 51 days ago

Verified 68d84d41

Fix out-of-bounds read in ConvTransposeWithDynamicPads (#32679)

bbernhar committed 52 days ago

Verified 2ecddca3

Fix GemmFloat8 C operand descriptor type (#31967)

apsonawane committed 52 days ago

Verified 6f863321

Validate recurrent input rank before access (#32348)

apsonawane committed 52 days ago

Verified eae1fd77

KleidiAI SVE2p1 halfgemm kernel integrated (#32670)

melkap01-Arm committed 52 days ago

Verified 0c245f72

[MLAS] Add RVV LinearAttention and ReduceMinimumMaximumF32 kernels for riscv64 (#32710)

velonica0 committed 52 days ago

Verified 86097f08

Older