microsoft/onnxruntime

Pull Requests Commits

Add internal capability planning types (S0)

Chi Lo committed 2 hours ago

7116b715

Handle kernel type string resolution errors without throwing (#33828)

mustjab committed 4 hours ago

Verified 1aae736a

Enable macOS compiler caching with shared sccache actions (#33811)

eserscor committed 8 hours ago

Verified 51aba5e4

[CUDA] Add 8-route grouped INT3 offload prefill, zero-cold doorbell short-circuit, and S=8 streaming optimizations (#33629)

tianleiwu committed 10 hours ago

Verified 5049049d

Validate LinearAttention head dimensions (#33821)

apsonawane committed 14 hours ago

Verified 19bcbb97

Add EP device memory capacity query API with CUDA support (#33447)

selenayang888 committed 14 hours ago

Verified 5f141934

[WebGPU] Fuse rank-32 quantized LoRA with MatMulNBits (#33370)

qjia7 committed 15 hours ago

Verified e64a8ae8

Fix spelling typos flagged by misspell linter (#33780)

adrastogi committed 16 hours ago

Verified 22c72f53

[CPU] Support right-padded prefill chunks in GroupQueryAttention (#33505)

tianleiwu committed 18 hours ago

Verified 3fc465dc

Use local Detox CLI in React Native CI (#33813)

eserscor committed 18 hours ago

Verified ee239433

Validate Attention head counts (#33498)

apsonawane committed 18 hours ago

Verified 7059e239

Validate MoE hidden dimensions (#33820)

apsonawane committed 18 hours ago

Verified 84e45d99

Verify downloaded Node packages (#33500)

apsonawane committed 19 hours ago

Verified d6f6bff4

Fix QMoE AVX2 lambda inline attributes for clang-cl (#33830)

mustjab committed 19 hours ago

Verified 902b02fd

Retain Node WebGPU output resources (#33741)

apsonawane committed 19 hours ago

Verified 34d4ec2a

Validate serialized prepacked buffers (#33499)

apsonawane committed 19 hours ago

Verified 6843e599

Validate Whisper timestamp token bounds (#33824)

apsonawane committed 19 hours ago

Verified 585d6a68

[CUDA] Optimize INT4 QMoE offload prefill/decode and S=8 doorbell execution (#33622)

tianleiwu committed 19 hours ago

Verified 8e59de3c

Validate Resize linear index bounds (#33497)

apsonawane committed 20 hours ago

Verified 1e4bfba8

[CUDA] Support right-padded prefill chunks in GroupQueryAttention (#33503)

tianleiwu committed 20 hours ago

Verified 734eea3e

[CUDA] Add Tensor-Core BF16 INT2 QMoE GEMV kernel and 3-mask BF16 converter (#33786)

tianleiwu committed 22 hours ago

Verified f42c839f

Fix PEP 668 failures in Linux host CI jobs (#33812)

eserscor committed 23 hours ago

Verified 8a8763e6

[CUDA] Add INT4 and INT3 QMoE CPU/GPU offload support (#33575)

tianleiwu committed 23 hours ago

Verified b69bd016

Fix: Add CMake package files to Windows artifact #28468 (#28897)

Jayashree-mcw committed 23 hours ago

Verified 4f5106d9

Fix JSEP Reshape and Unsqueeze schema registrations (#33749)

justinchuby committed 1 day ago

Verified 2650ca13

Update Kusto dashboard SDK dependencies to 6.0.0 (#33783)

mustjab committed 1 day ago

Verified 38960a12

Fix macOS vcpkg binary-cache environment identity (#33773)

eserscor committed 1 day ago

Verified 29dfb7bf

Skip MatMulAdd reshaping for zero-sized dimensions (#33766)

rookieLiu2018 committed 1 day ago

Verified 1b1d1e4d

Migrate GitHub Actions away from deprecated `macos-14` image (#33778)

edgchen1 committed 1 day ago

Verified c7bf7939

Bump follow-redirects from 1.16.0 to 1.16.2 in /js/web/test/e2e (#33796)

dependabot[bot] committed 1 day ago

Verified fb847a59

Older