Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
339 Open 17,302 Closed
339 Open 17,302 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

[QNN-EP] Dynamic EP Perf ep:QNN issues related to QNN exeution provider
#26122 opened Sep 22, 2025 by quic-calvnguy Loading…
3
[QNN EP] Add QAIRT Licensing file in QNN EP ep:QNN issues related to QNN exeution provider
#26121 opened Sep 22, 2025 by quic-tirupath Loading…
4
Allow vendor IDs in Python IOBinding device binds
#26119 opened Sep 22, 2025 by Jonahcb Loading…
2
Consistent with the configuration in the packaged cmake
#26104 opened Sep 20, 2025 by WangFengtu1996 Loading…
3
Write parameters based on output shapes not the amount of names ep:MIGraphX issues related to AMD MI GraphX execution provider
#26092 opened Sep 19, 2025 by TedThemistokleous Loading…
5
Update QMoE kernel with optimizations
#26091 opened Sep 19, 2025 by apsonawane Loading…
6
[QNN-EP] Support alternate Layernorm fusion pattern in QNN preprocess ep:QNN issues related to QNN exeution provider
#26060 opened Sep 16, 2025 by qti-mattsinc Loading…
2
Replace -infinity by lowest for masked values
#26055 opened Sep 16, 2025 by xadupre Loading…
7
Web/WASM: Copy back results for pre‑allocated CPU outputs (fixes #25786)
#26037 opened Sep 15, 2025 by Jonahcb Loading…
1
7
feat(tensorrt): add per-session use_tf32 provider option (#26029)
#26035 opened Sep 14, 2025 by Jonahcb Loading…
1
fix(layernorm): allow normalized_size==1 instead of error (#25896)
#26034 opened Sep 13, 2025 by Jonahcb Loading…
2
Register SimplifiedLayerNormalization to MS domain
#26033 opened Sep 12, 2025 by justinchuby Loading…
1
7
Debug failing cuda profiler test
#26032 opened Sep 12, 2025 by adrianlizarraga • Draft
1
[ARM CPU] SVE support for Sgemm kernel
#26027 opened Sep 12, 2025 by akote123 Loading…
15
Support plugin EPs with original SessionOptionsAppendExecutionProvider API
#26019 opened Sep 11, 2025 by adrianlizarraga • Draft
Fix #25890: update value_info when Gemm(transB=1) -> MatMul to avoid …
#26018 opened Sep 11, 2025 by Jonahcb Loading…
1
19
Adding documentation for device tensor creation using CreateMemoryInfo_V2 API in an EP agnostic way
#25995 opened Sep 9, 2025 by praneshgo Loading…
3
Update vcpkg to version 2025.08.27
#25993 opened Sep 9, 2025 by snnn • Draft
1
Bump reviewdog/action-shellcheck from 1.31.0 to 1.32.0 dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#25976 opened Sep 8, 2025 by dependabot bot Loading…
System.Numeric.Tensors breaking change fix
#25972 opened Sep 6, 2025 by tjwald Loading…
1
Clean up CUDA contrib ops folder
#25969 opened Sep 5, 2025 by hariharans29 Loading…
[TRT RTX EP] Rename TRT RTX libs to not collide with TRT
#25964 opened Sep 5, 2025 by gedoensmax Loading…
3
[webgpu] Move copy_kv_cache to template
#25961 opened Sep 5, 2025 by qjia7 • Draft
Add onnxruntime_plugin_ep_onnx_test for plugin EPs to run onnx test
#25942 opened Sep 4, 2025 by chilo-ms Loading…
3
[webgpu] Optimize flash decoding by merging QKT and SplitVx shader
#25929 opened Sep 3, 2025 by xiaofeihan1 Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.