Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
512 Open 14,351 Closed
512 Open 14,351 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

Fix syntax for some CoreML ML Program supported operator entries
#22268 opened Sep 30, 2024 by skottmckay Loading…
[build/openvino] fix build option when using use_openvino with hetero/multi/auto
#22266 opened Sep 29, 2024 by zoulee24 Loading…
Fix matmul nbits casts
#22265 opened Sep 29, 2024 by axodox Loading…
[WebNN EP] Support external data
#22263 opened Sep 29, 2024 by Honry Loading…
1
Make A100 jobs in PR checks again
#22261 opened Sep 29, 2024 by mszhanyi Loading…
Update phi3-python.md
#22260 opened Sep 28, 2024 by parinitarahi Loading…
Add MaxPool FP16 in XnnPack EP
#22258 opened Sep 28, 2024 by mszhanyi Loading…
10
enable serialize prepacked weights into data file
#22256 opened Sep 28, 2024 by frank-dong-ms Loading…
5
[webgpu-native] support webgpu profiling
#22255 opened Sep 28, 2024 by qjia7 • Draft
Fix equation in MatMulNBits op spec
#22253 opened Sep 27, 2024 by kunal-vaishnavi Loading…
4
[docs] Fix fp16 mixed precision example to reflect correct input variable names
#22250 opened Sep 27, 2024 by shubhambhokare1 Loading…
@shubhambhokare1
1
[webgpu-native] support for webgpu layernorms
#22249 opened Sep 27, 2024 by guschmue Loading…
6
parallize cast between fp32 and fp16
#22240 opened Sep 26, 2024 by liqunfu Loading…
1
Fix possible deadlock when using RunAsync
#22237 opened Sep 26, 2024 by DRKV333 Loading…
1
remove neural-speed
#22236 opened Sep 26, 2024 by yufenglee Loading…
2
Update documentation for Arm Compute Library
#22232 opened Sep 26, 2024 by MichaelTylerArm Loading…
[js/webgpu] Remove the limitation on axis in softmax ep:WebGPU ort-web webgpu provider
#22231 opened Sep 26, 2024 by gyagp Loading…
23
update the HTP power setting ep:QNN issues related to QNN exeution provider
#22227 opened Sep 26, 2024 by HectorSVC Loading…
1
Add S8U8 model type to GEMM and other quantized layers
#22226 opened Sep 26, 2024 by mguynn-intc Loading…
Replace gradle/wrapper-validation-action with gradle/actions/wrapper-validation-action
#22224 opened Sep 25, 2024 by jchen351 Loading…
3
Add microbenchmark for layer normalization
#22223 opened Sep 25, 2024 by amarin16 • Draft
1
[js/webgpu] Manage model download with a specific unittest option ep:WebGPU ort-web webgpu provider
#22214 opened Sep 25, 2024 by gyagp Loading…
8
Update quantization.md
#22211 opened Sep 25, 2024 by yy-shin Loading…
1
[Java] Add API for appending QNN EP
#22208 opened Sep 24, 2024 by edgchen1 Loading…
23
Update gradle version to 8.6
#22206 opened Sep 24, 2024 by jchen351 Loading…
1 task
4
ProTip! Follow long discussions with comments:>50.