Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
609 Open 19,004 Closed
609 Open 19,004 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

Use the latest version of AnyChart in the perf tool
#29636 opened Jul 9, 2026 by jacquerie Loading…
Fix structure of EpLibraryPlugin::Load so that we call Unload on error.
#29634 opened Jul 9, 2026 by skottmckay Contributor Loading…
4
Fix Qwen3 RotaryEmbedding fusion emitting invalid position_ids shape
#29632 opened Jul 9, 2026 by Sammy-Dabbas Contributor Loading…
1
Fix CUDA AveragePool wrong results with asymmetric padding and dilation ep:CUDA issues related to the CUDA execution provider
#29631 opened Jul 8, 2026 by titaiwangms Contributor Loading…
3
[WebGPU] Plugin EP 0.2.0 release cherry picks round 1
#29630 opened Jul 8, 2026 by edgchen1 Contributor Loading…
Fix CPU AvgPool ceil_mode + count_include_pad wrong average (opset 7-18 / MLAS path)
#29629 opened Jul 8, 2026 by titaiwangms Contributor Loading…
8
Fix JSEP pooling output shape to honor ceil_mode
#29627 opened Jul 8, 2026 by titaiwangms Contributor Loading…
7
Harden React Native iOS Detox CI against simulator shell crashes
#29626 opened Jul 8, 2026 by Copilot AI • Draft
@tianleiwu
Enable Spectre-mitigated MSVC libs for BinSkim builds
#29624 opened Jul 8, 2026 by tianleiwu Contributor Loading…
Hoist CropAndResize index offset to a named int64_t
#29623 opened Jul 8, 2026 by titaiwangms Contributor Loading…
Enable fpA_intB GEMM in CUDA builds and add configurable options release:1.28.0
#29622 opened Jul 8, 2026 by tianleiwu Contributor Loading…
16
Fix CPU FlashAttention disabled on Linux/aarch64 by detecting L2 cache via cpuinfo
#29621 opened Jul 8, 2026 by Sammy-Dabbas Contributor Loading…
1
2
[CUDA] Add cuDNN-free ArgMax/ArgMin and fix LogSoftmax on plugin EP release:1.28.0
#29620 opened Jul 8, 2026 by tianleiwu Contributor Loading…
8
[MLAS] Add AVX2 (+VNNI) 2-bit weight CPU kernels
#29619 opened Jul 8, 2026 by blazingphoenix7 Loading…
2
Fix type/shape inferencing double recursion for subgraphs
#29617 opened Jul 8, 2026 by skottmckay Contributor Loading…
2
Fix memory leak in GetOverridableInitializerNames()
#29616 opened Jul 8, 2026 by Copilot AI • Draft
1
@skottmckay
[Go] Add Go bindings for ONNX Runtime C API
#29615 opened Jul 8, 2026 by dannyota Loading…
1
3
[WebGPU] Optimize MatMulNBits wide-tile shader
#29611 opened Jul 8, 2026 by daijh Contributor Loading…
8
Bump onnx from 1.18.0 to 1.22.0 in /onnxruntime/python/tools/transformers/models/stable_diffusion/requirements dependencies Pull requests that update a dependency file python Pull requests that update Python code
#29608 opened Jul 8, 2026 by dependabot Bot Loading…
Weightless support for all initializers
#29607 opened Jul 7, 2026 by chilo-ms Contributor • Draft
5
Follow standard CMake semantics for CUDA architecture suffixes
#29601 opened Jul 7, 2026 by Sammy-Dabbas Contributor Loading…
1
3
fix(webgpu): use f32 accumulators in fp16 MatMul/MatMulNBits to prevent overflow (#26732)
#29599 opened Jul 7, 2026 by RobertoReale Loading…
1
16
Additional validation in LSTM and DynamicQuantizedLSTM
#29595 opened Jul 7, 2026 by skottmckay Contributor Loading…
Add Intel WebGPU subgroup-matrix MatMul implementation
#29592 opened Jul 7, 2026 by jchen10 Contributor Loading…
6
Fix usage of stream for memory pattern allocation with arena
#29589 opened Jul 7, 2026 by skottmckay Contributor Loading…
3
ProTip! Filter pull requests by the default branch with base:main.