- Notifications
You must be signed in to change notification settings - Fork3.5k
Pull requests: microsoft/onnxruntime
Author
Uh oh!
There was an error while loading.Please reload this page.
Label
Uh oh!
There was an error while loading.Please reload this page.
Projects
Uh oh!
There was an error while loading.Please reload this page.
Milestones
Uh oh!
There was an error while loading.Please reload this page.
Reviews
Assignee
Assigned to nobodyLoading
Uh oh!
There was an error while loading.Please reload this page.
Sort
Pull requests list
[DRAFT] Create a CUDA based memory arena instead of Cuda Allocator wrapped into BFCArena
#26535 openedNov 7, 2025 byyuslepukhin • Draft
[QNN-EP] Restrict zero pads validation check to NPU backend
#26534 openedNov 7, 2025 byqti-mattsincLoading…
[webgpu] Fix
GatherBlockQuantized on Intel ADL/TGL platforms #26526 openedNov 7, 2025 bydaijhLoading…
[QNN-EP] Remove outdated comment for per-channel quantization
#26523 openedNov 7, 2025 bychunghow-qtiLoading…
[VitisAI] Remove unused function body handling in graph fusion
#26519 openedNov 7, 2025 bymingyueliuhLoading…
Fix CUDA version hardcoding to support CUDA 13+ dynamically
#26518 openedNov 7, 2025 byGrigoryEvkoLoading…
Bump @react-native-community/cli and react-native in /js/react_native/e2e dependenciesPull requests that update a dependency file javascriptPull requests that update Javascript code
#26517 openedNov 7, 2025 bydependabotbotLoading…
[Build] update cuda 13 package: fatbin compress mode and cuda archs
#26516 openedNov 6, 2025 bytianleiwuLoading…
QDQ refactor: rename registration-phase functions to reflect their true meaning
#26511 openedNov 6, 2025 byrivkastrohLoading…
[QNN EP] documentation updates for the GPU backend.
#26508 openedNov 6, 2025 byjohnpaultakenLoading…
webgpu: fix dispatch size issue of Transpose operator ep:WebGPUort-web webgpu provider
#26501 openedNov 5, 2025 byxhcaoLoading…
[QNN EP] Adjust tolerance for Clip and Transpose tests due to FP16 default in QNN HTP
#26499 openedNov 5, 2025 byyuhuchua-qtiLoading…
[quant] Fix QuantizeLinear opset-23 kernel registration to match ONNX schema
#26491 openedNov 4, 2025 byrachelElfenbein-devLoading…
Bump ruff from 0.12.12 to 0.14.3 dependenciesPull requests that update a dependency file pythonPull requests that update Python code
#26478 openedNov 3, 2025 bydependabotbotLoading…
[WebGPU] Implement Split-K on Conv|MatMul ep:WebGPUort-web webgpu provider
#26461 openedOct 31, 2025 byJiawei-ShaoLoading…
[QNN-EP] - Tie HTP power config id lifetime to session
#26457 openedOct 30, 2025 byquic-calvnguyLoading…
ProTip! What’s not been updated in a month:updated:<2025-10-09.