[https://nvbugs/6050489][chore] unwaive tests

[bo-nv]

Summary by CodeRabbit

No user-visible changes

This release contains internal test infrastructure updates only. Test configuration waivers were adjusted for framework compatibility, with no impact to end-user functionality.

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.

[bo-nv]

/bot run --post-merge --disable-fail-fast

[coderabbitai]

📝 Walkthrough

Walkthrough

Modified test skip waivers in tests/integration/test_lists/waives.txt to update pytest parametrization exclusions: added a SKIP waiver for DeepSeekV3Lite bfloat16 tests with torch_compile=True and removed a SKIP waiver for Llama3.1 fp8 tests with torch_compile=False.

Changes

Test Skip Waiver Adjustments

Layer / File(s)	Summary
Test waiver adjustments for model variants tests/integration/test_lists/waives.txt	Updated SKIP waivers: added entry for TestDeepSeekV3Lite::test_bfloat16_4gpus with torch_compile=True configuration and removed entry for TestLlama3_1_8BInstruct::test_fp8_4gpus with torch_compile=False configuration.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14854: Both PRs modify tests/integration/test_lists/waives.txt to adjust SKIP entries for overlapping DeepSeekV3Lite bfloat16_4gpus/torch_compile configurations and Llama3.1_8BInstruct fp8/torch_compile cases.
• NVIDIA/TensorRT-LLM#8258: Both PRs modify tests/integration/test_lists/waives.txt to change which specific accuracy tests are skipped/unwaived (test selection via SKIP entries).

Suggested reviewers

• crazydemo
• jieli-matrix
• LarryXFly
• StanleySun639

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The pull request description is mostly empty template boilerplate with no actual content explaining the changes.	Fill in the Description section explaining which tests are being unwaived and why. Complete the Test Coverage section describing relevant tests. Provide details about the rationale for these changes.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title correctly identifies the main change: removing test waivers from the waives.txt file.
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.}

[bo-nv]

/bot run --post-merge --disable-fail-fast

[bo-nv]

/bot run --post-merge --disable-fail-fast

[bo-nv]

/bot run --post-merge --disable-fail-fast

[tensorrt-cicd]

PR_Github #51798 [ run ] triggered by Bot. Commit: 7aba527 Link to invocation

[tensorrt-cicd]

PR_Github #51798 [ run ] completed with state FAILURE. Commit: 7aba527
/LLM/main/L0_MergeRequest_PR pipeline #41162 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

[bo-nv]

/bot run

[bo-nv]

/bot run

[tensorrt-cicd]

PR_Github #51881 [ run ] triggered by Bot. Commit: 7aba527 Link to invocation

[tensorrt-cicd]

PR_Github #51881 [ run ] completed with state SUCCESS. Commit: 7aba527
/LLM/main/L0_MergeRequest_PR pipeline #41239 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

[bo-nv]

/bot run

[tensorrt-cicd]

PR_Github #51890 [ run ] triggered by Bot. Commit: 7aba527 Link to invocation

[tensorrt-cicd]

PR_Github #51890 [ run ] completed with state SUCCESS. Commit: 7aba527
/LLM/main/L0_MergeRequest_PR pipeline #41247 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation