[None][infra] Waive 1 failed cases for main in pre-merge 60603 - #19276
Conversation
Bug(s): 6786567 Requested by: @HuiGao-NV Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (1)
Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review. WalkthroughThe integration waiver list now skips ChangesSM103 test waiver
Priority: ⬇️ Low Estimated code review effort: 1 (Trivial) | ~2 minutes Change: Other Suggested reviewers: Merge Risk: ⚪ Minimal · up to This PR only skips the bug-linked SM103 test, with no concrete merge-blocking risk identified. 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
|
/bot skip --comment "waive only" |
|
Automatically added "ci: full pre-merge approved" because this PR has satisfied the required GitHub review approvals. Unresolved review conversations and other required checks remain independent merge requirements. |
|
PR_Github #74033 [ skip ] triggered by Bot. Commit: |
|
PR_Github #74033 [ skip ] completed with state |
Picks up the waiver for test_selfsampling_sm103_b512_k2048_cuda_graph (NVIDIA#19276, https://nvbugs/6786567), the only remaining pre-merge failure on this branch and not one this PR can cause. That test hardcodes a register-plan rung valid only at 148 SMs, so route() returns the main kernel on a GB300 node with a different SM count; it failed identically in all three builds on fb49597 (#60671, #60732, #60819) and was the sole failure in #60819. No conflicts, and this merge leaves the earlier _util.py resolution untouched. Co-Authored-By: Claude <noreply@anthropic.com> Signed-off-by: chenfeiz0326 <203214996+chenfeiz0326@users.noreply.github.com>
Auto-generated Waive PR
Created by: TensorRT LLM CI Report (requested by @HuiGao-NV)
Target branch:
mainBug(s): 6786567
Waive entries added
This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.
Dev Engineer Review
The change adds one
SKIPwaiver for the CUDA-graph self-sampling test. It does not change source code, APIs, or runtime behavior. The waiver references bug6786567.QA Engineer Review
The change modifies
tests/integration/test_lists/waives.txtand adds the waiver forunittest/_torch/thop/parallel/test_gvr_selfsampling_topk.py::test_selfsampling_sm103_b512_k2048_cuda_graph. No test implementation changes are included. The entry is in the waiver list; notest-db/orqa/list change is shown. Coverage verdict: needs follow-up because the test is skipped.Per-File QA Perspective
tests/integration/test_lists/waives.txt: Adds aSKIPwaiver for the CUDA-graph self-sampling top-k test and links it to bug6786567. QA should remove the waiver after the underlying failure is fixed.