[https://nvbugs/6427411][chore] Waive a failed test in Pre-merge

[shuyixiong]

Summary by CodeRabbit

• Tests
  • Added a new test waiver entry for a specific Llama 3.1 8B Instruct FP8 multi-GPU variant, aligning it with an existing tracked issue.

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)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• 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.

[shuyixiong]

/bot skip --comment "Waive test"

[coderabbitai]

📝 Walkthrough

Walkthrough

Added a single new waiver entry in the integration test waiver list, skipping a specific parameterized variant of the test_fp8_4gpus test for TestLlama3_1_8BInstruct, referencing bug nvbugs/6427411.

Changes

Waiver list update

Layer / File(s)	Summary
Add new test skip entry tests/integration/test_lists/waives.txt	Adds a SKIP entry for TestLlama3_1_8BInstruct::test_fp8_4gpus with tp2pp2-fp8kv=True-attn_backend=TRTLLM-torch_compile=False parameterization, referencing nvbugs/6427411.

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

Possibly related PRs

• NVIDIA/TensorRT-LLM#6795: Both PRs add new waiver/skip entries to the same waives.txt file.
• NVIDIA/TensorRT-LLM#16085: Both PRs add new SKIP entries for attention-related tests in the same waiver file.
• NVIDIA/TensorRT-LLM#16093: Both PRs add new waive/skip entries for failing test parameterizations to the same file.

Suggested reviewers: EmmaQiaoCh, yuxianq, dongxuy04

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is mostly the unfilled template and does not explain the issue, solution, or test coverage.	Add a short problem/solution summary and fill in Test Coverage with the relevant tests or waiver rationale.

✅ Passed checks (4 passed)

Check name	Status	Explanation
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.
Title check	✅ Passed	The title is concise, specific, and matches the waiver change with a valid NVBugs tag and chore type.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[tensorrt-cicd]

PR_Github #58173 [ skip ] triggered by Bot. Commit: 26fdfdc Link to invocation

[tensorrt-cicd]

PR_Github #58173 [ skip ] completed with state SUCCESS. Commit: 26fdfdc
Skipping testing for commit 26fdfdc

Link to invocation