Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
556 Open 18,672 Closed
556 Open 18,672 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

1.27.0 - cherry pick 1
#28817 opened Jun 5, 2026 by sanaa-hamel-microsoft Contributor Loading…
fix(ci): nodejs on nuget cuda 13 hangs release:1.27.0
#28816 opened Jun 5, 2026 by sanaa-hamel-microsoft Contributor Loading…
Fix XNNPACK Clip/Relu fusion when the producer output has other consumers
#28814 opened Jun 5, 2026 by tairenpiao Contributor Loading…
2
feat: add native CPU kernel for SequenceMap (opset 17)
#28813 opened Jun 5, 2026 by Rishi-Dave Contributor Loading…
1
10
[CoreML EP] Add Equal builder
#28807 opened Jun 5, 2026 by maxwbuckley Contributor • Draft
3
Fix stale output shape metadata in WebGPU external-data E2E model
#28805 opened Jun 5, 2026 by Copilot AI • Draft
@tianleiwu
[WebGPU] Enable Cast to int64 by default
#28804 opened Jun 5, 2026 by fanchenkong1 Contributor Loading…
5
webgpu: Normalize indirect-dispatch buffer in flash attention
#28803 opened Jun 5, 2026 by qjia7 Contributor Loading…
6 tasks done
webgpu: Normalize indirect-dispatch buffer in flash attention
#28802 opened Jun 5, 2026 by qjia7 Contributor Loading…
6 tasks done
Address Lora shortcomings
#28801 opened Jun 5, 2026 by yuslepukhin Member Loading…
5
Clarify and improve ownership semantics Model Editor C/C++ API
#28800 opened Jun 5, 2026 by yuslepukhin Member Loading…
1
23
Fix thread-pool param self-assignment and dedupe schema registration in session_state_test
#28799 opened Jun 5, 2026 by GopalakrishnanN Contributor Loading…
3
Log EP version on inference failure and in EpDeviceUsage event, Log ORT version
#28794 opened Jun 4, 2026 by dabhattimsft Contributor Loading…
4
Add session.qdq_strip_activations option for QDQ models
#28793 opened Jun 4, 2026 by jambayk Contributor Loading…
docs: Update outdated documentation pages
#28791 opened Jun 4, 2026 by Copilot AI Loading…
1
@justinchuby
10
creates zips to consume cuda plugin ep from foundry local
#28789 opened Jun 4, 2026 by prathikr Contributor Loading…
3
[MLAS][KleidiAI] Add MLAS Arm64 half GEMM and convolution support
#28786 opened Jun 4, 2026 by Laan33 Contributor Loading…
7
Hint GCC >= 12 on aarch64 for bf16/fp16 capability probes
#28785 opened Jun 4, 2026 by Rishi-Dave Contributor Loading…
1
6
Drop QDQ around MaxPool for opset 22 and stabilize ASAN build_x64
#28783 opened Jun 4, 2026 by Copilot AI Loading…
1
@xadupre
3
Fix Type-confusion: raw-pointer bind_input causing OOB write
#28781 opened Jun 4, 2026 by selenayang888 Contributor Loading…
10
Fix INT64 initializer data propagation
#28778 opened Jun 3, 2026 by GopalakrishnanN Contributor Loading…
9
Relax CompileModel validation to accept zero-input OrtModel graphs
#28771 opened Jun 3, 2026 by adrastogi Contributor Loading…
1
1
Add BFloat16 support analysis and plan for CPU and CUDA execution providers
#28769 opened Jun 3, 2026 by Copilot AI • Draft
1
@justinchuby
Fix MLAS AVX2 build failure on toolchains without AVX-VNNI assembler support
#28767 opened Jun 3, 2026 by Copilot AI • Draft
1
@hariharans29
2
docs: add external data file handling section to PyTorch export tuto…
#28764 opened Jun 3, 2026 by CandyButcher27 Loading…
2
ProTip! What’s not been updated in a month: updated:<2026-05-05.