Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
322 Open 17,214 Closed
322 Open 17,214 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

Quant tool: Don't store original outputs in MinMax Calibrator
#26321 opened Oct 16, 2025 by jambayk Loading…
3
feat: Add BFloat16 support for Gemm and MatMul CPU operators
#26317 opened Oct 15, 2025 by snnn Loading…
11
Use time_costs_total for output_stats
#26313 opened Oct 15, 2025 by keshavv27 Loading…
2
docs: update EP support table
#26310 opened Oct 15, 2025 by nekomeowww Loading…
1
[WebNN] Fallback int64 indices to int32
#26308 opened Oct 15, 2025 by Honry Loading…
29
[CUDA] Adjust package build settings for Blackwell GPU
#26307 opened Oct 14, 2025 by tianleiwu • Draft
Address MLAS NchwcBlockSize for AMD64 platforms behavior in the minimal builds release:1.23.2
#26306 opened Oct 14, 2025 by yuslepukhin Loading…
8
fix npm publishing
#26305 opened Oct 14, 2025 by guschmue Loading…
2
Allow present_key to be empty when past_key is provided in Attention
#26303 opened Oct 14, 2025 by justinchuby Loading…
6
Implement FP32 kleidiai Gemv
#26302 opened Oct 14, 2025 by JonathanC-ARM Loading…
2
Implement multithreading in qgemm_kleidi
#26301 opened Oct 14, 2025 by melkap01-Arm Loading…
3
Fix for micro benchmark build failure with c++20
#26299 opened Oct 14, 2025 by JonathanC-ARM Loading…
3
[webgpu] Support RotaryEmbedding in flash attention ep:WebGPU ort-web webgpu provider
#26297 opened Oct 14, 2025 by xiaofeihan1 Loading…
14
[QNN EP] Reshape Transpose pattern fusion for 6D tensors
#26296 opened Oct 14, 2025 by quic-ashwshan Loading…
[webgpu] Remove 'webgpu' suffix from filenames ep:WebGPU ort-web webgpu provider
#26287 opened Oct 13, 2025 by daijh Loading…
2
Bump github/codeql-action from 3 to 4 dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#26286 opened Oct 13, 2025 by dependabot bot Loading…
Bump ruff from 0.12.12 to 0.14.0 dependencies Pull requests that update a dependency file python Pull requests that update Python code
#26285 opened Oct 13, 2025 by dependabot bot Loading…
[LARCH64 CPU]Provide inference acceleration optimization for Loongson CPU with 4-bit quantized models
#26280 opened Oct 12, 2025 by movedancer Loading…
19
Add partial data propagation to enhance shape inference
#26269 opened Oct 9, 2025 by chilo-ms Loading…
28
Add support to filter_ep_devices using ep or device metadata in perftest
#26255 opened Oct 7, 2025 by jnagi-intel Loading…
16
[QNN EP] Upgrade QNN to 2.39.0
#26249 opened Oct 6, 2025 by qti-jkilpatrick Loading…
10
[QNN-EP] Support pad op pre-opset11
#26248 opened Oct 6, 2025 by qti-mattsinc Loading…
[DRAFT] Allow EP to provide additional HW devices
#26234 opened Oct 3, 2025 by adrianlizarraga • Draft
5
[QNN-EP] Apply Softmax layout transformation for GPU
#26233 opened Oct 3, 2025 by qti-mattsinc Loading…
[MIGraphX EP] Fix dangling graph outputs nodes being promoted to output nodes when graph not split ep:MIGraphX issues related to AMD MI GraphX execution provider
#26224 opened Oct 3, 2025 by TedThemistokleous Loading…
11
ProTip! Add no:assignee to see everything that’s not assigned.