Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
505 Open 14,038 Closed
505 Open 14,038 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

[JS/WebGPU] Avoid producing presentKey/presentValue outputs if pastKey/pastValue … ep:WebGPU ort-web webgpu provider
#21782 opened Aug 17, 2024 by satyajandhyala Loading…
4
Add session and run option workload_type for applications to set efficient mode.
#21781 opened Aug 17, 2024 by AlbertGuan9527 Loading…
ORT Training 1.19.0 Release: Cherry Pick Round 0
#21780 opened Aug 17, 2024 by prathikr Loading…
fix mha for in the case that present kv is not consumed ep:WebGPU ort-web webgpu provider
#21777 opened Aug 16, 2024 by guschmue Loading…
10
[java] Fix for OnnxTensor creation when passing in a ByteBuffer containing elements of a different type
#21774 opened Aug 16, 2024 by Craigacp Loading…
[WebNN EP] Support Erf and Trilu for CPU backend
#21768 opened Aug 16, 2024 by Honry Loading…
8
[js] add big data file to formatter ignore list
#21767 opened Aug 16, 2024 by fs-eire Loading…
[Fix] Make python API doc generation in Microsoft-hosted Agent
#21766 opened Aug 16, 2024 by mszhanyi Loading…
[QNN EP] Apply workaround for Conv validation bug when bias input is implicit ep:QNN issues related to QNN exeution provider
#21764 opened Aug 16, 2024 by adrianlizarraga • Draft
update size limit check of training GPU wheel
#21762 opened Aug 15, 2024 by mszhanyi Loading…
Matmul-nbit to support fp16 activation
#21760 opened Aug 15, 2024 by liqunfu • Draft
[TensorRT EP] Set cuda 12 as default for ORT 1.19
#21758 opened Aug 15, 2024 by yf711 Loading…
2
Apply/bring back UseSharedPrePackedBuffers for mlas in matmul-nbit
#21756 opened Aug 15, 2024 by liqunfu Loading…
ORT 1.19.0 Release: Cherry Pick Round 2.5
#21755 opened Aug 15, 2024 by prathikr Loading…
ConvTranpose using CUDNN Frontend with NHWC support
#21752 opened Aug 15, 2024 by JTischbein Loading…
14
[js/webgpu] optimize MatmulNBits
#21747 opened Aug 15, 2024 by qjia7 Loading…
14
adjust orttraining binary size test
#21741 opened Aug 14, 2024 by prathikr Loading…
3
Pr21721
#21735 opened Aug 14, 2024 by zz002 • Draft
[JS/WebGPU] Add GatherBlockQuantized op support ep:WebGPU ort-web webgpu provider
#21734 opened Aug 14, 2024 by satyajandhyala Loading…
2
Bump axios from 1.6.1 to 1.7.4 in /js/node dependencies Pull requests that update a dependency file javascript Pull requests that update Javascript code
#21732 opened Aug 14, 2024 by dependabot bot Loading…
Added implementation of fix_output_shape function without 2gb limit
#21729 opened Aug 13, 2024 by DavitGrigoryan132 Loading…
1
[TensorRT EP] Remove the dependency on CUDA allocators in CUDA EP
#21727 opened Aug 13, 2024 by chilo-ms • Draft
1
Add option for compiler flags.
#21721 opened Aug 13, 2024 by NK-microsoft Loading…
2
Remove duplicated einsum defs for ROCm, use hipify.
#21718 opened Aug 13, 2024 by mindest • Draft
[VitisAI] remove wrong error msg, required by Microsoft
#21715 opened Aug 13, 2024 by BoarQing Loading…
7
ProTip! What’s not been updated in a month: updated:<2024-07-18.