Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
513 Open 14,797 Closed
513 Open 14,797 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

[TensorRT EP] Use TRT/CUDA/ORT version from runtime instead of build time to generate hash value
#22921 opened Nov 21, 2024 by chilo-ms Loading…
WIP: FlashAttention for WebGPU EP
#22919 opened Nov 21, 2024 by sushraja-msft Loading…
Add option to force generic algorithms on x86
#22917 opened Nov 21, 2024 by AlekseiNikiforovIBM Loading…
7
[VSINPU]Split\Pad and some element-wise OPs support
#22916 opened Nov 21, 2024 by xuke537 Loading…
2
[js/webgpu] support FlashAttention-2 for attention operator ep:WebGPU ort-web webgpu provider
#22915 opened Nov 21, 2024 by xhcao Loading…
9
MlasTranspose multi-threads support.
#22912 opened Nov 21, 2024 by msy-kato Loading…
1
Update transformers test requirements
#22911 opened Nov 21, 2024 by tianleiwu • Draft
[QNN EP] [DRAFT] Support Conv float weight/bias.
#22906 opened Nov 20, 2024 by adrianlizarraga • Draft
Update Onnxruntime download version for GenAI
#22900 opened Nov 20, 2024 by ajindal1 Loading…
1
Override android qnn sdk version with pipeline param
#22895 opened Nov 19, 2024 by sheetalarkadam Loading…
1
Update Intel Thread Counts
#22894 opened Nov 19, 2024 by A-Satti Loading…
3
[TensorRT EP] Add new provider option to exclude specific ops from running on TRT
#22892 opened Nov 19, 2024 by chilo-ms • Draft
#22890 Fix profiling on empty Optional
#22891 opened Nov 19, 2024 by amancini-N Loading…
1
Quantize Bias for Conv/Gemm on Quantized Model
#22889 opened Nov 19, 2024 by centwang • Draft
Add Optional Activation node to NodeUnit
#22888 opened Nov 19, 2024 by centwang • Draft
7
[js/webgpu] Enable graph capture with memcpy
#22883 opened Nov 19, 2024 by axinging • Draft
[WebNN] Support negative steps for slice ep:WebNN WebNN execution provider
#22871 opened Nov 18, 2024 by shiyi9801 Loading…
27
Build DML in Windows GPU CI pipeline
#22869 opened Nov 18, 2024 by mszhanyi • Draft
Refactor emulator start and stop functions for clarity and efficiency platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#22861 opened Nov 16, 2024 by jchen351 Loading…
@skottmckay
31
Keep the model metadata on the generated EP context model (use bridge api)
#22860 opened Nov 15, 2024 by chilo-ms Loading…
[TensorRT EP] Fix wrong input order when generating IndexedSubGraph
#22857 opened Nov 15, 2024 by chilo-ms Loading…
Enable QNN HTP spill fill buffer setting to save RAM usage. ep:QNN issues related to QNN exeution provider
#22853 opened Nov 15, 2024 by HectorSVC Loading…
5
Int4 support
#22850 opened Nov 15, 2024 by BoarQing • Draft
[js/webgpu] Add GatherND ep:WebGPU ort-web webgpu provider
#22847 opened Nov 15, 2024 by axinging Loading…
11
Update Android SDK version to 34, Gradle version to 8.7 and Java Version to 17 platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#22846 opened Nov 15, 2024 by jchen351 Loading…
ProTip! Follow long discussions with comments:>50.