Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
456 Open 17,991 Closed
456 Open 17,991 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

[QNN-EP] Parallelize graph finalization
#27629 opened Mar 12, 2026 by quic-calvnguy • Draft
3
[Cuda Plugin] Refactor CUDA ops — Move more shared CPU/CUDA helper code from .cc to headers (Part 2)
#27628 opened Mar 12, 2026 by tianleiwu • Draft
4
[QNN-EP] Disable file mapping for embedded cache
#27627 opened Mar 12, 2026 by quic-calvnguy Loading…
3
Add PE version info to onnxruntime_providers_vitisai.dll
#27626 opened Mar 11, 2026 by xhan65 Loading…
1
Use SafeInt in implementation of Col2Im
#27625 opened Mar 11, 2026 by fs-eire Loading…
1
Allow comments in build.py argument files
#27624 opened Mar 11, 2026 by edgchen1 Loading…
feat: use ccache for reusable linux
#27623 opened Mar 11, 2026 by sanaa-hamel-microsoft • Draft
[Optimizer] Fix ConstantFolding crash with missing optional outputs
#27620 opened Mar 11, 2026 by TsofnatMaman Loading…
1
[Cuda Plugin] Refactor CUDA ops — Move shared CPU/CUDA helper code from .cc to headers
#27617 opened Mar 11, 2026 by tianleiwu Loading…
9
Optimize ONNX Attention KV cache with ConcatNewToPast and add release-build kernel safety
#27613 opened Mar 10, 2026 by titaiwangms Loading…
44
Release Packaging Pipeline Orchestration
#27611 opened Mar 10, 2026 by kpkbandi Loading…
21
Add support to fetch device type from EP subgraph assignment
#27610 opened Mar 10, 2026 by adrastogi • Draft
1
[MLAS][KleidiAI]Catlaw01/sgemm epilogue neon opt
#27609 opened Mar 10, 2026 by Laan33 Loading…
9
[Plugin EP] Make compiled kernel names "more" unique
#27608 opened Mar 10, 2026 by apwojcik Loading…
Use _tpause instead of __builtin_ia32_tpause
#27607 opened Mar 10, 2026 by mocknen Loading…
8
[Node.js] Implement runSync
#27604 opened Mar 10, 2026 by uasan Loading…
[CUDA] Add Validation of batch_indices in RoiAlign
#27603 opened Mar 9, 2026 by tianleiwu Loading…
15
[TensorRT RTX] Fix compiler warnings on Linux and Windows
#27602 opened Mar 9, 2026 by gedoensmax Loading…
6
ONNX 1.21.0 integration
#27601 opened Mar 9, 2026 by titaiwangms • Draft
1
36
Add a new session option, mlas.disable_kleidiai_sme.
#27598 opened Mar 9, 2026 by Colm-in-Arm Loading…
Add validation of position_ids in RotaryEmbedding operators
#27597 opened Mar 9, 2026 by tianleiwu Loading…
12
[WebGPU] Allow reusing an external GPUDevice via env.webgpu.device ep:WebGPU ort-web webgpu provider
#27596 opened Mar 9, 2026 by fdb Loading…
1
[POC] Annotation based partitioning along with resource accounting
#27595 opened Mar 9, 2026 by yuslepukhin • Draft
11
Expose Python OrtDeviceVendorId enum and use it for vendor-aware OrtDevice aliases
#27594 opened Mar 9, 2026 by tianleiwu Loading…
2
[QNN EP] ETW log level rule change
#27593 opened Mar 9, 2026 by qti-ashwshan Loading…
ProTip! no:milestone will show everything without a milestone.