Skip to content

[https://nvbugs/6507110][chore] Unwaive TestQwen3_30B_A3B::test_nvfp4 dep4_latency_moe_trtllm - #17294

Open
sunnyqgg wants to merge 1 commit into
NVIDIA:mainfrom
sunnyqgg:unwaive-6507110
Open

[https://nvbugs/6507110][chore] Unwaive TestQwen3_30B_A3B::test_nvfp4 dep4_latency_moe_trtllm#17294
sunnyqgg wants to merge 1 commit into
NVIDIA:mainfrom
sunnyqgg:unwaive-6507110

Conversation

@sunnyqgg

@sunnyqgg sunnyqgg commented Aug 5, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Remove the waive for accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_trtllm-torch_compile=False] (https://nvbugs/6507110).
  • Original post-merge failure was 'Test terminated unexpectedly' with no Python stack trace (SLURM infra wrapping only), flagged FLAKY (2 failures in 30 days).
  • Repair Bot could not reproduce: multiple runs on two different B300 x4 nodes (umb-b300-020, umb-b300-dp-148) all passed on current main.

Test plan

  • CI passes; the test runs again in its post-merge B300 stage.

Dev Engineer Review

  • Removed the waiver for TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_trtllm-torch_compile=False].
  • The change uses the correct waiver-list format.
  • No duplicate waiver entry or unintended scope change was found.
  • The removal is consistent with the reported successful Repair Bot runs.

QA Engineer Review

  • Modified tests/integration/test_lists/waives.txt.
  • Removed one waived test entry.
  • No test-db/ or qa/ files were modified.
  • CBTS coverage data is unavailable. Verdict: needs follow-up.

… dep4_latency_moe_trtllm

Signed-off-by: qgai <qgai@nvidia.com>
@coderabbitai

coderabbitai Bot commented Aug 5, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: b1b0b3d0-0946-4d9c-9e9d-b8ac0628f160

📥 Commits

Reviewing files that changed from the base of the PR and between 7608520 and 8da735f.

📒 Files selected for processing (1)
  • tests/integration/test_lists/waives.txt
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt

Walkthrough

The pull request removes one waived Qwen3 NVFP4 test entry from the integration test waiver list.

Changes

Cohort / File(s) Summary
Test waiver update
tests/integration/test_lists/waives.txt
Removes the waiver for TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_trtllm-torch_compile=False].

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

Suggested reviewers: brnguyen2

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title identifies the NVBug, uses the chore type, and clearly states that the test waiver was removed.
Description check ✅ Passed The description explains the waiver removal, failure history, reproduction results, and CI test plan.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches 💡 1
🛠️ Fix failing CI checks 💡
  • Create stacked PR
  • Commit on current branch
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands.

@sunnyqgg

sunnyqgg commented Aug 5, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #63979 [ run ] triggered by Bot. Commit: 8da735f Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #63979 [ run ] completed with state SUCCESS. Commit: 8da735f
/LLM/main/L0_MergeRequest_PR pipeline #51914 completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ Action Required:

  • Please check the failed tests and fix your PR
  • If you cannot view the failures, ask the CI triggerer to share details
  • Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants