Uh oh!
There was an error while loading. Please reload this page.
[ExecuTorch][WebGPU] Cover Conv1d routes and dynamic manifests - #21601
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21601
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 678f21c with merge base ad3a71f ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a |
Stack from ghstack (oldest at bottom):
Cover Conv1d routing, resize, and dynamic manifest replay
Static numeric coverage pins the general groups=1 Conv1d kernel while preserving pointwise and depthwise routing. The manifest harness now separates upper-bound export inputs from live runtime inputs so dynamic execution proves a distinct shape through one loaded graph.
Key changes:
Case.export_inputsandCase.dynamic_shapescarry export-time samples and constraints whileCase.inputsremains the live runtime input.This is coverage-only; runtime kernels are unchanged.
Co-authored-with: Claude Code.
Differential Revision: D114936144