Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
893 Open 19,683 Closed
893 Open 19,683 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

u24 image override
#32635 opened Sep 16, 2026 by kpkbandi Contributor • Draft
Reject nodes that feed inputs to a zero-input operator schema
#32633 opened Sep 16, 2026 by shiyi (shiyi9801) Contributor Loading…
5
Fix CUDA GQA graph replay test diagnostics
#32632 opened Sep 16, 2026 by Copilot AI • Draft
@justinchuby
1
[MLAS] Fix fp16 overflow/NaN bugs in ARM64 NEON Gelu/Erf and add extreme-value test coverage
#32631 opened Sep 16, 2026 by kjg0724 (kjg0724) Contributor Loading…
4
[WebGPU] Refactor MatMul algorithm selection
#32630 opened Sep 16, 2026 by Jiajia Qin (qjia7) Contributor • Draft
[WebGPU] Fix mixed-type LayerNormalization shaders
#32629 opened Sep 16, 2026 by Jiajia Qin (qjia7) Contributor • Draft
1
4
[WebNN EP] Support NHWC layout in Resize by inferring resample2d axes
#32628 opened Sep 16, 2026 by Wanming Lin (Honry) Contributor Loading…
4
Enable opt-in host-pageable CUDA GatherBlockQuantized
#32626 opened Sep 16, 2026 by Copilot AI Loading…
@kunal-vaishnavi
10
[CUDA] Address cuDNN paged SDPA review feedback
#32624 opened Sep 16, 2026 by Tianlei Wu (tianleiwu) Contributor Loading…
5
[WebGPU] checks to handle oob writes based on seqlens_k ep:WebGPU ort-web webgpu provider
#32623 opened Sep 15, 2026 by Edward Chen (edgchen1) Contributor Loading…
7
Add Arm KleidiAI compatibility documentation
#32622 opened Sep 15, 2026 by damdoo001-arm Loading…
9
Optimize CPU uint8 GatherBlockQuantized dequantization
#32621 opened Sep 15, 2026 by Copilot AI Loading…
@kunal-vaishnavi
5
Add review guidance for deprecated components
#32620 opened Sep 15, 2026 by Edward Chen (edgchen1) Contributor Loading…
5
[CUDA] Enable non-causal PagedAttention with small cache pages
#32619 opened Sep 15, 2026 by Copilot AI Loading…
@tianleiwu
2
[CUDA][WebGPU] Add packed sparse attention indexer for continuous batching
#32618 opened Sep 15, 2026 by Copilot AI • 3/3 Loading…
@kunal-vaishnavi
10
Add GQA workspace estimation ep:CUDA issues related to the CUDA execution provider memory
#32617 opened Sep 15, 2026 by Ti-Tai Wang (titaiwangms) Contributor Loading…
4
Improve CPU provider build time with Eigen PCH
#32616 opened Sep 15, 2026 by Ti-Tai Wang (titaiwangms) Contributor Loading…
1
Optimize single-source WebGPU SparsePagedAttention
#32613 opened Sep 15, 2026 by Copilot AI • 3/3 Loading…
@kunal-vaishnavi
19
Fix heap buffer overflow from reusing a packed sub-byte buffer for a full-byte tensor
#32611 opened Sep 15, 2026 by Wei Wang (wangw-1991) Contributor Loading…
5
Fix out-of-bounds read in EmbedLayerNormalization shape inference for scalar beta
#32610 opened Sep 15, 2026 by Wei Wang (wangw-1991) Contributor Loading…
4
Fix out-of-bounds read when a Loop/Scan body input is also an initializer
#32609 opened Sep 15, 2026 by Wei Wang (wangw-1991) Contributor Loading…
4
[MLAS] Add RVV fused activation fast path on riscv64
#32608 opened Sep 15, 2026 by ww8191201-coder Loading…
5
Harden shape inference for contrib ops
#32607 opened Sep 15, 2026 by shiyi (shiyi9801) Contributor Loading…
7
[WebNN EP] Support GroupNormalization, GroupNorm and SkipGroupNorm
#32606 opened Sep 15, 2026 by Wanming Lin (Honry) Contributor Loading…
6
[WebGPU] Widen SubgroupMatrixMatMulNBits tile size to 128x256
#32605 opened Sep 15, 2026 by Jianhui Dai (daijh) Contributor • Draft
4
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.