Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
561 Open 15,495 Closed
561 Open 15,495 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Further reduce work load for Mac CI pipeline
#24197 opened Mar 27, 2025 by fs-eire Loading…
Set shared memory type based on options during the compilation phase
#24196 opened Mar 26, 2025 by quic-ashigarg Loading…
5
Enable mapping of buffers allocated on CPU in the NPU address space
#24195 opened Mar 26, 2025 by quic-ashigarg Loading…
26
Disable KleidiAI in Python Packaging pipeline MacOS build
#24194 opened Mar 26, 2025 by edgchen1 Loading…
Remove all CG template from pipelines
#24193 opened Mar 26, 2025 by jchen351 Loading…
Ensure to use correct GPU device in RunSince when it's invoked by new thread
#24192 opened Mar 26, 2025 by chilo-ms Loading…
Move Linux ARM64 CI pipeline and Linux DNNL CI pipeline to Github Actions
#24190 opened Mar 26, 2025 by snnn Loading…
[CUDA] upgrade cudnn front end to 1.11
#24189 opened Mar 26, 2025 by tianleiwu Loading…
Cherry picks for 1.21.1
#24188 opened Mar 26, 2025 by amarin16 Loading…
Support Gemma3 with Clip fused attention
#24187 opened Mar 26, 2025 by titaiwangms • Draft
[WIP][Native WebGPU] Add Conv, ConTranspose and FusedConv ep:WebGPU ort-web webgpu provider
#24186 opened Mar 26, 2025 by satyajandhyala • Draft
8
[webgpu-ep] Fix test_batchnorm_example ep:WebGPU ort-web webgpu provider
#24184 opened Mar 26, 2025 by jchen10 Loading…
12
[QNN-EP] Enhance QNN-EP support for Softmax with opset < 13. ep:QNN issues related to QNN exeution provider
#24180 opened Mar 26, 2025 by quic-zhaoxul Loading…
3
Validation CreateSessionFromArray with ep.context_enable enabled
#24176 opened Mar 25, 2025 by HectorSVC Loading…
2
Fuse Initializers Graph Transform
#24175 opened Mar 25, 2025 by sunnyshu-intel Loading…
[WebGPU EP] Implements If Operator ep:WebGPU ort-web webgpu provider
#24171 opened Mar 25, 2025 by prathikr • Draft
1
Rolling back the python/cuda
#24170 opened Mar 25, 2025 by jchen351 Loading…
[webgpu] optimize SkipLayerNormalization operator ep:WebGPU ort-web webgpu provider
#24164 opened Mar 25, 2025 by xhcao Loading…
9
[WIP] hack to investigate parallelization settings
#24147 opened Mar 24, 2025 by xadupre Loading…
Improve Shape Inference for GQA
#24143 opened Mar 24, 2025 by peishenyan Loading…
7
[WebNN] Support MatMulNBits op ep:WebNN WebNN execution provider
#24142 opened Mar 24, 2025 by Honry Loading…
1
[Doc] EPContext with weight sharing
#24141 opened Mar 24, 2025 by HectorSVC Loading…
15
Bump ruff from 0.9.5 to 0.11.2 dependencies Pull requests that update a dependency file python Pull requests that update Python code
#24140 opened Mar 24, 2025 by dependabot bot Loading…
Fix #24130 by adding an empty dependency group to the code that generates Microsoft.ML.OnnxRuntime.nuspec
#24131 opened Mar 21, 2025 by benjamin-hodgson Loading…
4
[webgpu] Use 64 as the workgroup size of DP4AMatMulQuantize ep:WebGPU ort-web webgpu provider
#24129 opened Mar 21, 2025 by qjia7 Loading…
ProTip! Add no:assignee to see everything that’s not assigned.