[https://nvbugs/6112497][test] Unwaive passing test

[yihwang-nv]

Summary

• Unwaive accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=TRTLLM-torch_compile=False] (nvbugs/6112497).

Test plan

• CI confirms the unwaived test passes on the pp4 + TRTLLM attention backend configuration.

Summary by CodeRabbit

• Tests
  • Removed a test waiver for PyTorch LLM accuracy testing on multi-GPU configurations, enabling validation of the previously skipped test.

[coderabbitai]

📝 Walkthrough

Walkthrough

A single test waiver entry for Llama3.1 8B Instruct bfloat16 inference with pipeline parallelism (pp4) has been removed from the test waiver list, allowing the test accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=TRTLLM-torch_compile=False] to run.

Changes

Test Waiver Update

Layer / File(s)	Summary
Test waiver removal tests/integration/test_lists/waives.txt	Removed one SKIP waiver entry for the Llama3.1 8B Instruct bfloat16 test with pipeline parallelism of 4, previously waived for nvbugs/6112497.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14158: Both PRs change tests/integration/test_lists/waives.txt by removing a SKIP waiver entry for an accuracy/test_llm_api_pytorch.py test case.
• NVIDIA/TensorRT-LLM#14221: Both PRs modify the same tests/integration/test_lists/waives.txt by adding/removing individual SKIP test-waiver entries.
• NVIDIA/TensorRT-LLM#13641: Both PRs modify the same test waiver file (tests/integration/test_lists/waives.txt) by removing specific SKIP entries for particular LLM test configurations.

Suggested reviewers

• jieli-matrix
• xinhe-nv
• StanleySun639

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The pull request description provides a clear summary of the change (unwaiving a test) and references the associated bug ID. However, it is missing several key sections from the template including PR title format, detailed explanation, and PR checklist completion.	Add PR title following the template format [ticket][type] Summary. Complete the PR checklist and provide more context if available about why the test is now passing.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title correctly references the NVBugs ticket and test type, and accurately describes the main change of removing a test waiver.
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.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[yihwang-nv]

/bot run --extra-stage "DGX_B300-4_GPUs-PyTorch-Post-Merge-1,DGX_B300-4_GPUs-PyTorch-Post-Merge-2,GB200-4_GPUs-PyTorch-Post-Merge-1,GB300-4_GPUs-PyTorch-Post-Merge-1,GB30
0-4_GPUs-PyTorch-Post-Merge-2"

[tensorrt-cicd]

PR_Github #49689 [ run ] triggered by Bot. Commit: fe2ae03 Link to invocation

[tensorrt-cicd]

PR_Github #49689 [ run ] completed with state FAILURE. Commit: fe2ae03
/LLM/main/L0_MergeRequest_PR pipeline #39296 completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

[yihwang-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #49886 [ run ] triggered by Bot. Commit: fe2ae03 Link to invocation

[tensorrt-cicd]

PR_Github #49886 [ run ] completed with state SUCCESS. Commit: fe2ae03
/LLM/main/L0_MergeRequest_PR pipeline #39464 completed with status: 'SUCCESS'

CI Report

Link to invocation