Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
445 Open 13,534 Closed
445 Open 13,534 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

Update Torch Version to Fix ATen CPU Pipeline Failure
#20845 opened May 29, 2024 by er3x3 Loading…
Update bigmodels-ci-pipeline.yml: move the job to A100 machines
#20843 opened May 29, 2024 by snnn Loading…
fix typo in QNN backend
#20842 opened May 28, 2024 by zhouwg Loading…
[Quant tool] Extend support for QDQ type conversion at graph output
#20841 opened May 28, 2024 by adrianlizarraga Loading…
1
Add ACPT docs to ORT docs
#20839 opened May 28, 2024 by sophies927 Loading…
8
[BUILD] Do not require custom protoc exec for --arm64 or --arm64ec on arm64 host
#20838 opened May 28, 2024 by adrianlizarraga • Draft
7
Add device tensor documentation for GPU execution providers
#20837 opened May 28, 2024 by gedoensmax Loading…
5
adding publishing stage to publish java CUDA 12 pkg to ado
#20834 opened May 28, 2024 by jchen351 Loading…
[WebNN EP] Support latest WebNN softmax op ep:WebNN WebNN execution provider
#20827 opened May 27, 2024 by Honry Loading…
7
Update build from source instructions
#20819 opened May 25, 2024 by natke Loading…
Split java's gradle build and test
#20817 opened May 24, 2024 by jchen351 Loading…
[js/webnn] update API of session options for WebNN
#20816 opened May 24, 2024 by fs-eire Loading…
8
[JS/WebGPU] Use getByOffset/setByOffset instead of getByIndices/setByIndices. ep:WebGPU ort-web webgpu provider
#20815 opened May 24, 2024 by satyajandhyala • Draft
[WIP] Implement FlashAttention for CPU
#20805 opened May 24, 2024 by duanqn • Draft
4
Release backward inputs per static graph ref count training issues related to ONNX Runtime training; typically submitted using template
#20804 opened May 24, 2024 by pengwa Loading…
Create c-api-gpu.yml template
#20797 opened May 24, 2024 by jchen351 • Draft
deprecate total seqlen
#20793 opened May 23, 2024 by aciddelgado Loading…
2
[JS/WebGPU] Map Reshape operator with int64_t data type to JSEP.
#20789 opened May 23, 2024 by satyajandhyala • Draft
[WebNN EP] Remove legacy MLOperandDescriptor.type ep:WebNN WebNN execution provider
#20783 opened May 23, 2024 by Honry Loading…
11
[WebNN EP] Add data type constraint ep:WebNN WebNN execution provider
#20779 opened May 23, 2024 by Honry Loading…
15
relax seq len checking in rotary_emb
#20778 opened May 23, 2024 by wejoncy Loading…
2
Upgrade min ios version to 14.0
#20773 opened May 22, 2024 by snnn • Draft
[Build] Change onnxruntime_NVCC_THREADS from option to cache entry
#20768 opened May 22, 2024 by decahedron1 Loading…
1
6
add hipify-clang requirement to rocm ep eps.md
#20764 opened May 22, 2024 by AidenPierce616 Loading…
[WebNN EP] Validate MLContext creation early to allow fallback to other EP ep:WebNN WebNN execution provider
#20735 opened May 20, 2024 by Honry Loading…
3
ProTip! Adding no:label will show everything without a label.