[https://nvbugs/5725811][test] Remove outdated llama-v4 and ministral-8b models out of QA scope

[yufeiwu-nv]

Summary by CodeRabbit

• Tests
  • Removed model configuration entry for starcoder2_7b.
  • Updated GPU condition labels in test configuration.
  • Removed specific test case variants from performance testing suite.

Description

Several nvbugs mentioned llamav4 is low-prioirty, such as 5725811, 5717074.
mistral-8b is outdated mentioned in 5823781.
Remove them out of QA test scope.

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.

[yufeiwu-nv]

/bot skip --comment "only test list modify"

[coderabbitai]

📝 Walkthrough

Walkthrough

These changes remove the starcoder2_7b model path entry from test configuration and eliminate associated test cases for llama_v4_* model variants from the test suite, while consolidating GPU group labels in test condition comments.

Changes

Cohort / File(s)	Summary
Test Configuration Removals tests/integration/defs/perf/test_perf.py, tests/integration/test_lists/qa/llm_perf_core.yml	Removed starcoder2_7b model path entry and deleted multiple llama_v4_* test cases across various GPU condition blocks. Renumbered and consolidated GPU group labels in comments (removed entries "11", "12", "13" and replaced with consolidated "11", "12" entries).

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	PR description provides context (NVBug references) but lacks a proper PR title and has incomplete Test Coverage section.	Add a properly formatted PR title following [type] convention (e.g., [test] Remove llama-v4 model from QA scope) and complete the Test Coverage section explaining how the removal is validated.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Title check	✅ Passed	The title clearly and specifically describes the main change: removing outdated llama-v4 and ministral-8b models from QA scope, which directly aligns with the changeset modifications.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

📝 Coding Plan

• Generate coding plan for human review comments

---

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

[tensorrt-cicd]

PR_Github #39563 [ skip ] triggered by Bot. Commit: cb9cfe8 Link to invocation

[tensorrt-cicd]

PR_Github #39563 [ skip ] completed with state SUCCESS. Commit: cb9cfe8
Skipping testing for commit cb9cfe8

Link to invocation

[yufeiwu-nv]

/bot skip --comment "only test list modify"

[tensorrt-cicd]

PR_Github #39674 [ skip ] triggered by Bot. Commit: af9d423 Link to invocation

[tensorrt-cicd]

PR_Github #39674 [ skip ] completed with state SUCCESS. Commit: af9d423
Skipping testing for commit af9d423

Link to invocation