Skip to content

Pull requests: microsoft/onnxruntime

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

add headers in onnxrt wheel
#26908 opened Jan 5, 2026 by abhilash-pinapaka Draft
Address some issues and fix VS 2026 build
#26905 opened Jan 5, 2026 by skottmckay Loading…
[webgpu] Add ScatterElements support
#26903 opened Jan 4, 2026 by qjia7 Loading…
Update genai API docs
#26900 opened Jan 2, 2026 by natke Loading…
Update GQA benchmark to support bfloat16
#26898 opened Jan 2, 2026 by tianleiwu Loading…
[MLAS] Fix building on FreeBSD / powerpc64le
#26895 opened Jan 2, 2026 by pkubaj Loading…
Allow choosing memory type for CudaPinned allocator
#26892 opened Jan 2, 2026 by AndreyOrb Loading…
[webgpu] Support any batch size for dp4a matmul path
#26884 opened Dec 31, 2025 by qjia7 Loading…
Add option to delay creation of intra-op threadpool
#26881 opened Dec 30, 2025 by skottmckay Loading…
Update TRT to 10.14
#26871 opened Dec 28, 2025 by eserscor Loading…
HeadUpdate README.md
#26866 opened Dec 27, 2025 by muradrk10-dev Loading…
Plugin EP API - Add OrtEp::IsConcurrentRunSupported
#26859 opened Dec 24, 2025 by edgchen1 Loading…
[QNN EP] Add RMSNorm Op support in QNN EP ep:QNN issues related to QNN exeution provider
#26853 opened Dec 22, 2025 by tirupath-qti Loading…
[webgpu] Optimize AttentionPrepare ep:WebGPU ort-web webgpu provider
#26850 opened Dec 22, 2025 by qjia7 Loading…
Added support for QMX kernels in MLAS
#26849 opened Dec 22, 2025 by qti-vaiskv Loading…
[QNN] Support QNN HTA backend through better Op validation (#26739) ep:QNN issues related to QNN exeution provider
#26848 opened Dec 22, 2025 by MarwanNIbrahim Loading…
ProTip! Follow long discussions with comments:>50.