[https://nvbugs/6168859][chore] Waive test_openai_chat_guided_decoding on all GPUs

[tburt-nv]

Description

The model behavior seems to be flaky, which causes the test to fail randomly.

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.

Summary by CodeRabbit

• Tests
  • Updated integration test waiver list by modifying skip list entries for guided decoding tests with new bug reference tracking for improved issue correlation and test management.

[tburt-nv]

/bot skip --comment "waive only check"

[coderabbitai]

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: 1c6878c4-c45b-40fe-81e5-5af30ce1ad1d

📥 Commits

Reviewing files that changed from the base of the PR and between 0435722 and d278fda.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This PR updates the integration test waiver list by removing a hardware-specific waiver for test_openai_chat_guided_decoding on H100 and adding a generalized waiver entry with a reference to bug tracking issue nvbugs/6168859.

Changes

Test Waiver List Update

Layer / File(s)	Summary
Update guided decoding test waiver tests/integration/test_lists/waives.txt	Existing waiver for full:H100/test_e2e.py::test_openai_chat_guided_decoding[openai/gpt-oss-120b] is removed and replaced with a generalized waiver entry for the same test case, now tracking nvbugs/6168859.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~5 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14228: Also modifies tests/integration/test_lists/waives.txt by removing and updating test waiver entries.
• NVIDIA/TensorRT-LLM#14062: Modifies the same integration test waiver file by adding and removing specific skipped test cases with nvbugs references.
• NVIDIA/TensorRT-LLM#13196: Changes the same test waiver list file by removing and updating specific test waiver entries.

Suggested reviewers

• crazydemo
• jieli-matrix
• LarryXFly
• StanleySun639

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The description provides the reason for the waiver (flaky model behavior) but lacks detail about which test is being waived and test coverage information.	Provide more specific details about the test being waived and explicitly reference the bug or issue causing the flakiness.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically summarizes the main change: waiving a flaky test across all GPUs with the associated bug reference.
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.}

[tensorrt-cicd]

PR_Github #49215 [ skip ] triggered by Bot. Commit: d278fda Link to invocation

[tensorrt-cicd]

PR_Github #49215 [ skip ] completed with state SUCCESS. Commit: d278fda
Skipping testing for commit d278fda

Link to invocation