Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Pull requests: microsoft/onnxruntime

New pull request New
359 Open 17,454 Closed
359 Open 17,454 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

[Migrphax] Fix docker file
#26737 opened Dec 6, 2025 by tianleiwu • Draft
[Doc] Remove rocm build from source instructions
#26733 opened Dec 5, 2025 by tianleiwu Loading…
3
Bump transformers from 4.52.3 to 4.53.0 in /onnxruntime/python/tools/transformers/models/whisper dependencies Pull requests that update a dependency file python Pull requests that update Python code
#26731 opened Dec 4, 2025 by dependabot bot Loading…
Bump transformers from 4.52.1 to 4.53.0 in /tools/ci_build/requirements/transformers-test dependencies Pull requests that update a dependency file python Pull requests that update Python code
#26730 opened Dec 4, 2025 by dependabot bot Loading…
Add 28 + 35 to CMake download_retry_codes
#26729 opened Dec 4, 2025 by ssstr1pe Loading…
1
[QNN EP] Implement Platform-Aware UT Skipping Infra for QNN
#26728 opened Dec 4, 2025 by quic-boyuc • Draft
1
[DONT REVIEW]Expand test sizes in GenerateGemmParams function
#26727 opened Dec 4, 2025 by xiaofeihan1 Loading…
[webgpu] Add CeilDiv into webgpu utils ep:WebGPU ort-web webgpu provider
#26723 opened Dec 4, 2025 by daijh Loading…
9
[webgpu] Optimize Attention by enhancing flash attention support
#26715 opened Dec 3, 2025 by qjia7 • Draft
8
upgrade emsdk to v4.0.21
#26713 opened Dec 3, 2025 by fs-eire • Draft
3
[EP ABI] Update Graph_GetGraphView() implementation
#26711 opened Dec 3, 2025 by chilo-ms Loading…
6
[QNN EP] Add Static bias encoding support for Conv op
#26710 opened Dec 2, 2025 by quic-ashwshan Loading…
Build issues on AIX for POWER10 and POWER11
#26704 opened Dec 2, 2025 by KV2773 Loading…
15
[QNN-EP] Enable skip_qnn_version_check in qnn unit test
#26703 opened Dec 2, 2025 by qti-hungjuiw Loading…
1
[VitisAI] Add support compiled model compatibility information retrieval and validation
#26699 opened Dec 2, 2025 by mingyueliuh Loading…
3
blog: Add community blog for ONNX usage in Ionic
#26698 opened Dec 2, 2025 by theopolis Loading…
[QNN EP] Default to HTP instead of using last provided device
#26696 opened Dec 2, 2025 by qti-mattsinc • Draft
1
Implement new experimental lookup-based matrix multiplication method(TMAC)
#26695 opened Dec 1, 2025 by vraspar • Draft
Simplify & optimize Arm64 NCHWc Convolution kernels
#26691 opened Dec 1, 2025 by Rohanjames1997 Loading…
9
[MLAS/NEON] Add dedicated kernel for depthwise convolution for ARM64 using NEON intrinsics
#26688 opened Dec 1, 2025 by hariharans29 Loading…
17
Bump ruff from 0.12.12 to 0.14.7 dependencies Pull requests that update a dependency file python Pull requests that update Python code
#26685 opened Dec 1, 2025 by dependabot bot Loading…
Symbolic shape inference of Shape should use start and end attribute
#26683 opened Nov 28, 2025 by Bludator Loading…
[QNN EP] Enablement of 64bit Udma mode ep:QNN issues related to QNN exeution provider
#26677 opened Nov 28, 2025 by qti-monumeen Loading…
WebGPU: Transpose Conv kernels in Prepack ep:WebGPU ort-web webgpu provider
#26675 opened Nov 28, 2025 by jchen10 Loading…
6
[webgpu] Support int64 for range
#26673 opened Nov 27, 2025 by qjia7 • Draft
ProTip! Exclude everything labeled bug with -label:bug.
Morty Proxy This is a proxified and sanitized view of the page, visit original site.