Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
578 Open 18,884 Closed
578 Open 18,884 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

Add MoeCudaQuantizer to onnxruntime.quantization
#29509 opened Jul 3, 2026 by tianleiwu Contributor Loading…
[webgpu] Enable im2col-matmul for newer Xe platforms; limit to fp16
#29505 opened Jul 3, 2026 by daijh Contributor Loading…
1
Detach C++ node tests from ONNX on-disk data/node artifacts (onnx#7959) + retiring equivalence proof + corpus-collapse tripwire
#29504 opened Jul 2, 2026 by titaiwangms Contributor Loading…
8
Shard Windows ASan test runs
#29503 opened Jul 2, 2026 by edgchen1 Contributor Loading…
3
[Packaging] Packaging onnxruntime-node for macOS x86-64
#29502 opened Jul 2, 2026 by hariharans29 Member Loading…
1
12
Model package: fold external_data into session options and remove legacy directory load path
#29501 opened Jul 2, 2026 by jambayk Contributor Loading…
7
[CUDA] Support prepacked fpA_intB weights in MatMulNBits
#29499 opened Jul 2, 2026 by tianleiwu Contributor • Draft
7
[web] Support Blob-backed external data for on-demand loading in JSPI builds
#29477 opened Jul 2, 2026 by kylo5aby • Draft
1
1
Add int32 support for CPU Trilu
#29476 opened Jul 2, 2026 by the0cp Contributor Loading…
1
[WebNN EP] Fix scale/zero_point rank for per-axis QDQ on last axis
#29475 opened Jul 2, 2026 by Honry Contributor Loading…
1
[CUDA] Online tuning of the MatMulNBits small-M batched GEMV cap
#29469 opened Jul 2, 2026 by jambayk Contributor • Draft
7
Upgrade to Xcode 26
#29468 opened Jul 2, 2026 by edgchen1 Contributor • Draft
2
[MLAS] Add ARM64 2-bit weight CPU kernels
#29466 opened Jul 1, 2026 by hariharans29 Member Loading…
9
Validate Conv bias tensor size against output channel count to prevent OOB read
#29464 opened Jul 1, 2026 by chilo-ms Contributor Loading…
adjusts conv kernel to use get/set by offset helpers
#29463 opened Jul 1, 2026 by prathikr Contributor Loading…
1
3
Validate per-element split sizes on the input-tensor path to prevent OOB read
#29461 opened Jul 1, 2026 by chilo-ms Contributor Loading…
Bump transformers from 4.52.3 to 5.3.0 in /onnxruntime/python/tools/transformers/models/whisper dependencies Pull requests that update a dependency file python Pull requests that update Python code
#29460 opened Jul 1, 2026 by dependabot Bot Loading…
Honor model_external_initializers_file_folder_path for file-path model loads
#29459 opened Jul 1, 2026 by jambayk Contributor Loading…
5
Add strided tensor design
#29458 opened Jul 1, 2026 by yuslepukhin Contributor Loading…
5
Fix a regression in graph-capture session initialization that rejects an empty graph
#29457 opened Jul 1, 2026 by adrastogi Contributor Loading…
6
[js/webgpu] Add DFT operator
#29454 opened Jul 1, 2026 by nicholascelestin Loading…
1
2
[QNN-EP] Add reshape handler when Reshape merges contiguous and ascending permuted axes
#29453 opened Jul 1, 2026 by quic-muchhsu Contributor Loading…
Clamp 1D attention mask_index to valid bounds
#29449 opened Jun 30, 2026 by tianleiwu Contributor Loading…
2 of 4 tasks
Validate B/scales/zero_points shape in MatMulNBits::PrePack
#29445 opened Jun 30, 2026 by apsonawane Contributor Loading…
5
Guard MlasConvPrepare working-buffer products with SafeInt
#29444 opened Jun 30, 2026 by apsonawane Contributor Loading…
5
ProTip! no:milestone will show everything without a milestone.