Skip to content

[https://nvbugs/6070878][fix] Skip gemma3 fp8 test only on L40S#13009

Closed
brb-nv wants to merge 1 commit intoNVIDIA:mainfrom
brb-nv:user/brb/specific-waive-on-l40s
Closed

[https://nvbugs/6070878][fix] Skip gemma3 fp8 test only on L40S#13009
brb-nv wants to merge 1 commit intoNVIDIA:mainfrom
brb-nv:user/brb/specific-waive-on-l40s

Conversation

@brb-nv
Copy link
Copy Markdown
Collaborator

@brb-nv brb-nv commented Apr 13, 2026

Description

Currently, this test is waives across all archs. This MR waives only on the problem arch L40S - this is considered low-priority for now. So, not fixing it.

Test Coverage

pytest -vs accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_fp8_prequantized

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.

Summary by CodeRabbit

  • Tests
    • Updated test skip configurations for GPU compatibility scenarios to ensure proper test execution across different hardware configurations.

@brb-nv brb-nv requested a review from xinhe-nv April 13, 2026 18:12
@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai bot commented Apr 13, 2026

📝 Walkthrough

Walkthrough

Updated skip selectors in the test waives list for TestGemma3_1BInstruct::test_fp8_prequantized tests by adding the full:sm89/ prefix to both torch_compile configurations, maintaining the same SKIP URL reference.

Changes

Cohort / File(s) Summary
Test Skip List
tests/integration/test_lists/waives.txt
Added full:sm89/ prefix to skip selectors for TestGemma3_1BInstruct::test_fp8_prequantized with torch_compile=False and torch_compile=True; SKIP URL remains unchanged at https://nvbugs/6070878.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name Status Explanation Resolution
Description check ❓ Inconclusive The PR description explains the change (narrowing test waiver to L40S only) and provides test coverage command, but the title is missing the required format and some context is unclear. Add a properly formatted PR title following [JIRA ticket/NVBugs ID/GitHub issue/None][type] Summary pattern. Clarify what 'arch L40S' means and why this architecture is problematic.
✅ Passed checks (2 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly and concisely describes the main change: narrowing a test waiver to a specific architecture (L40S) for the Gemma3 FP8 test.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ 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.

@brb-nv brb-nv force-pushed the user/brb/specific-waive-on-l40s branch from 1a0343c to e8e411d Compare April 13, 2026 18:16
@brb-nv
Copy link
Copy Markdown
Collaborator Author

brb-nv commented Apr 14, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43118 [ run ] triggered by Bot. Commit: e8e411d Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43118 [ run ] completed with state FAILURE. Commit: e8e411d
/LLM/main/L0_MergeRequest_PR pipeline #33752 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

Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
@brb-nv brb-nv force-pushed the user/brb/specific-waive-on-l40s branch from e8e411d to 8118775 Compare April 14, 2026 16:41
@brb-nv
Copy link
Copy Markdown
Collaborator Author

brb-nv commented Apr 14, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43262 [ run ] triggered by Bot. Commit: 8118775 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43262 [ run ] completed with state SUCCESS. Commit: 8118775
/LLM/main/L0_MergeRequest_PR pipeline #33815 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

@brb-nv brb-nv closed this Apr 15, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants