Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
380 Open 17,650 Closed
380 Open 17,650 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix some issues when building with the latest CUDA and cuDNN versions
#27049 opened Jan 17, 2026 by skottmckay Loading…
Bump version to 1.25.0
#27048 opened Jan 17, 2026 by tianleiwu Loading…
1
Version increment for 1.23.3
#27047 opened Jan 16, 2026 by adrastogi Loading…
3
Disable Float32_2Bits_Asymmetric_256x256 test release:1.24.0
#27046 opened Jan 16, 2026 by vraspar Loading…
[QNN EP] Add FusedMatMul operator support release:1.24.0
#27044 opened Jan 16, 2026 by tirupath-qti Loading…
16
[JS/WebGPU] Fix Split operator handling of dynamic shapes ep:WebGPU ort-web webgpu provider
#27043 opened Jan 16, 2026 by jarrelscy Loading…
5
Fix incorrect warning suppression in projects using precompiled headers on Windows
#27039 opened Jan 16, 2026 by skottmckay Loading…
3
[webgpu] support arbitrary input_channel size for im2col
#27038 opened Jan 16, 2026 by wenqinI • Draft
2
Move model compatibility checks ahead of session initialization release:1.24.0
#27037 opened Jan 16, 2026 by adrastogi • Draft
[QNN-EP] Fix UT failures for Gemm, Resize, and Einsum
#27036 opened Jan 16, 2026 by yuhuchua-qti Loading…
Add Provides-Dist metadata to onnxruntime variant packages
#27035 opened Jan 16, 2026 by Copilot AI • Draft
@fs-eire
[QNN EP] Add QuickGELU operator support for QNN provider release:1.24.0
#27034 opened Jan 16, 2026 by tirupath-qti Loading…
19
[Reland] Attention(23) CUDA
#27030 opened Jan 15, 2026 by titaiwangms Loading…
upgrade emsdk to 4.0.23
#27029 opened Jan 15, 2026 by fs-eire Loading…
add support for DFT with onesided=True and inverse=True (irfft)
#27028 opened Jan 15, 2026 by simonbyrne Loading…
Add a new pipeline for CUDA 13 nuget builds release:1.24.0
#27023 opened Jan 15, 2026 by eserscor Loading…
9
Add INT2 and UINT2 support for QDQ, transpose and cast ops release:1.24.0
#27022 opened Jan 15, 2026 by vraspar Loading…
12
Fix pytorch comparisonFix: Replace duplicate OpenVINO code with PyTorch code in comparison section
#27019 opened Jan 15, 2026 by chaya2350 Loading…
1
Fix the bug in setting _fallback_providers
#27018 opened Jan 15, 2026 by nimdrak Loading…
1
Add dedicated API to support extracting compatibility string from model metadata release:1.24.0
#27015 opened Jan 15, 2026 by adrastogi Loading…
8
Fix ConfigEps execution provider ordering in test files
#27014 opened Jan 15, 2026 by fs-eire Loading…
refactor common test target settings
#27013 opened Jan 15, 2026 by fs-eire Loading…
2
Publish both Cuda 13 and Cuda 12 packages in packaging pipeline
#27012 opened Jan 14, 2026 by eserscor • Draft
8
Dev/erscor/2026/1/10 jar testing release:1.24.0
#27011 opened Jan 14, 2026 by eserscor Loading…
4
[webgpu] Support CopyTensors with offsets
#27004 opened Jan 14, 2026 by qjia7 • Draft
13
ProTip! no:milestone will show everything without a milestone.