Skip to content

[https://nvbugs/5826604][test] Remove test waive for Llama3.1 8B bfloat16 4gpu timeout …#12092

Merged
syuoni merged 1 commit intoNVIDIA:mainfrom
syuoni:enweiz/remove-waive-5826604
Mar 12, 2026
Merged

[https://nvbugs/5826604][test] Remove test waive for Llama3.1 8B bfloat16 4gpu timeout …#12092
syuoni merged 1 commit intoNVIDIA:mainfrom
syuoni:enweiz/remove-waive-5826604

Conversation

@syuoni
Copy link
Collaborator

@syuoni syuoni commented Mar 11, 2026

…(NVBug 5826604)

Remove the test waiver for TestLlama3_1_8BInstruct::test_bfloat16_4gpus [tp4-attn_backend=TRTLLM-torch_compile=True].

The test was waived due to intermittent timeout on GB200 (NVBug 5826604). After investigation, the test passes consistently on GB200 with the current codebase (10/10 runs passed, ~104s each). Re-enabling to verify stability in CI.

Summary by CodeRabbit

  • Chores
    • Removed a test waiver entry, re-enabling validation for a previously excluded test case.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

  • PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

  • PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

  • Test cases are provided for new code paths (see test instructions)

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • Update tava architecture diagram if there is a significant design change in PR.

  • The reviewers assigned automatically/manually are appropriate for the PR.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

…(NVBug 5826604)

Remove the test waiver for TestLlama3_1_8BInstruct::test_bfloat16_4gpus
[tp4-attn_backend=TRTLLM-torch_compile=True].

The test was waived due to intermittent timeout on GB200 (NVBug 5826604).
After investigation, the test passes consistently on GB200 with the current
codebase (10/10 runs passed, ~104s each). Re-enabling to verify stability
in CI.

Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Mar 11, 2026

📝 Walkthrough

Walkthrough

A single test waiver entry is removed from the waives list. The entry for test_bfloat16_4gpus[tp4-attn_backend=TRTLLM-torch_compile=True] in the Llama3.1 8B Instruct test suite is no longer explicitly skipped.

Changes

Cohort / File(s) Summary
Test Waiver Configuration
tests/integration/test_lists/waives.txt
Removed one test waiver entry for a bfloat16 GPU test case with TRTLLM attention backend and torch compilation enabled.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name Status Explanation Resolution
Description check ❓ Inconclusive PR description partially addresses required template sections with clear explanation of issue and solution, but Test Coverage section is empty and PR checklist items lack substantive commentary. Fill in the Test Coverage section by listing the re-enabled test and how it validates the fix. Add notes explaining which checklist items apply to this waiver removal.
✅ Passed checks (2 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly references the NVBugs ID and describes the main change: removing a test waiver for a specific Llama3.1 test case.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

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

@syuoni
Copy link
Collaborator Author

syuoni commented Mar 11, 2026

/bot run --stage-list "GB200-4_GPUs-PyTorch-1, GB200-4_GPUs-PyTorch-2"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #38513 [ run ] triggered by Bot. Commit: cfda0bb Link to invocation

@tensorrt-cicd
Copy link
Collaborator

PR_Github #38513 [ run ] completed with state SUCCESS. Commit: cfda0bb
/LLM/main/L0_MergeRequest_PR pipeline #29862 (Partly Tested) completed with status: 'SUCCESS'

Link to invocation

@syuoni syuoni requested a review from EmmaQiaoCh March 11, 2026 06:12
@syuoni
Copy link
Collaborator Author

syuoni commented Mar 11, 2026

/bot skip --comment "Unwaived test passed"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #38544 [ skip ] triggered by Bot. Commit: cfda0bb Link to invocation

@tensorrt-cicd
Copy link
Collaborator

PR_Github #38544 [ skip ] completed with state SUCCESS. Commit: cfda0bb
Skipping testing for commit cfda0bb

Link to invocation

@syuoni syuoni merged commit 6739c11 into NVIDIA:main Mar 12, 2026
8 checks passed
@syuoni syuoni deleted the enweiz/remove-waive-5826604 branch March 12, 2026 02:26
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