Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
390 Open 17,771 Closed
390 Open 17,771 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

Bump protobuf from 4.25.8 to 5.29.6 in /onnxruntime/python/tools/transformers/models/llama dependencies Pull requests that update a dependency file python Pull requests that update Python code
#27259 opened Feb 5, 2026 by dependabot bot Loading…
Bump protobuf from 4.25.8 to 5.29.6 in /tools/ci_build/github/linux/docker/inference/aarch64/python/cpu/scripts dependencies Pull requests that update a dependency file python Pull requests that update Python code
#27258 opened Feb 5, 2026 by dependabot bot Loading…
Log Framework name to more Windows ML relevant events
#27256 opened Feb 5, 2026 by angelser Loading…
Bump protobuf from 6.33.0 to 6.33.5 in /tools/ci_build/requirements/transformers-test dependencies Pull requests that update a dependency file python Pull requests that update Python code
#27255 opened Feb 5, 2026 by dependabot bot Loading…
Bump protobuf from 6.33.0 to 6.33.5 in /tools/ci_build/github/windows/python dependencies Pull requests that update a dependency file python Pull requests that update Python code
#27254 opened Feb 5, 2026 by dependabot bot Loading…
Add thread pool work callbacks API
#27253 opened Feb 5, 2026 by sdotpeng • Draft
1
[Shape Inference] Fix GQA shape inference for present outputs
#27250 opened Feb 5, 2026 by Honry Loading…
1
Fix WebGPU Conv auto_pad=SAME_UPPER padding calculation ep:WebGPU ort-web webgpu provider
#27249 opened Feb 5, 2026 by ingyukoh Loading…
1
3
[Core] Expose a session option to disable NCHWc layout optimizations
#27248 opened Feb 5, 2026 by hariharans29 Loading…
10
[CUDA] GroupQueryAttention with XQA and Quantized KV Cache Support
#27246 opened Feb 5, 2026 by tianleiwu • Draft
4
Add ARM Neon kernels for 2 bit LUT Gemm
#27244 opened Feb 4, 2026 by vraspar • Draft
Fix LSTM clipping before h activation (Issue #27224)
#27239 opened Feb 4, 2026 by chaya2350 Loading…
1
2
[WebNN] Support more features for GQA ep:WebNN WebNN execution provider
#27234 opened Feb 4, 2026 by Honry Loading…
10
Doc fixes
#27228 opened Feb 3, 2026 by edgchen1 Loading…
Only reduce the range when in force symmetric case
#27222 opened Feb 2, 2026 by yiliangbetter Loading…
1
[MLAS] Fix Lut GEMM Flakiness and Accuracy release:1.24.2
#27216 opened Jan 30, 2026 by tianleiwu Loading…
8
[QNN EP] Enablement of sustained high performance mode
#27212 opened Jan 30, 2026 by qti-monumeen Loading…
[WebGPU EP] Remove unused has_bias in MatMul::ComputeInternal
#27211 opened Jan 30, 2026 by Jiawei-Shao • Draft
3
Local builds for onnxruntime-node that include OpenVINO EP
#27205 opened Jan 29, 2026 by MarioGini • Draft
[CUDA] Support volumetric (3-D) grid sampling in the CUDA GridSample operator
#27201 opened Jan 29, 2026 by hariharans29 Loading…
4
3
build: Make sympy an optional dependency
#27200 opened Jan 29, 2026 by ingyukoh Loading…
3
Early exit if external initializer files are missing when compiling
#27199 opened Jan 29, 2026 by adrianlizarraga • Draft
tg-autopilot D start
#27198 opened Jan 29, 2026 by ArsenKhanamiryan Loading…
1
Session config to create weightless EPContext models during compilation
#27197 opened Jan 28, 2026 by adrianlizarraga • Draft
1
Avoid repetitive creation of fp4/fp8 native-custom-op domains for NvTensorRtRtx EP
#27192 opened Jan 28, 2026 by vishalpandya1990 Loading…
6
ProTip! no:milestone will show everything without a milestone.