[https://nvbugs/6093715][fix] AutoDeploy: skip nvfp4 test pre-blackwell

[galagam]

Summary by CodeRabbit

• Tests
  • Enhanced hardware compatibility validation to skip model tests on unsupported platforms.
  • Removed a test waiver entry to align test execution with current hardware requirements.

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)

• 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.

[galagam]

/bot run

[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: 7f132f82-91aa-4af5-a9b1-661b55e6553c

📥 Commits

Reviewing files that changed from the base of the PR and between f3e458e and cd42acd.

📒 Files selected for processing (2)

• tests/integration/defs/accuracy/test_llm_api_autodeploy.py
• tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

These changes update the test configuration for the NVFP4 model by adding a skip-pre-Blackwell mark to the AutoDeploy test parameterization and removing a corresponding waive entry from the waive list, consolidating hardware compatibility checks.

Changes

Cohort / File(s)	Summary
NVFP4 Test Configuration tests/integration/defs/accuracy/test_llm_api_autodeploy.py, tests/integration/test_lists/waives.txt	Added skip_pre_blackwell mark to NVFP4 model entry in AutoDeploy parameterization and removed corresponding waive entry for the same configuration, consolidating pre-Blackwell hardware skip logic.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description contains only the template with no actual content filled in under Description, Test Coverage, or implementation details.	Fill in the Description section explaining why NVFP4 tests need to be skipped pre-Blackwell and list the affected test cases in Test Coverage section.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately reflects the main change: adding skip_pre_blackwell mark to NVFP4 model test to skip on unsupported hardware.
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 #45675 [ run ] triggered by Bot. Commit: cd42acd Link to invocation

[tensorrt-cicd]

PR_Github #45675 [ run ] completed with state FAILURE. Commit: cd42acd

Link to invocation

[galagam]

/bot run

[tensorrt-cicd]

PR_Github #45713 [ run ] triggered by Bot. Commit: cd42acd Link to invocation

[tensorrt-cicd]

PR_Github #45713 [ run ] completed with state FAILURE. Commit: cd42acd
/LLM/main/L0_MergeRequest_PR pipeline #35915 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

Link to invocation

[galagam]

/bot run

[tensorrt-cicd]

PR_Github #45756 [ run ] triggered by Bot. Commit: cd42acd Link to invocation