Skip to content

[https://nvbugs/5522746][fix] unwaive tests caused by node issues after rebooting - #8193

Merged
chzblych merged 1 commit into
NVIDIA:mainfrom
lancelly:unwaive_tests
Oct 9, 2025
Merged

[https://nvbugs/5522746][fix] unwaive tests caused by node issues after rebooting#8193
chzblych merged 1 commit into
NVIDIA:mainfrom
lancelly:unwaive_tests

Conversation

@lancelly

@lancelly lancelly commented Oct 8, 2025

Copy link
Copy Markdown
Collaborator

After internal cluster reboot, the tests seems allright. Unwaive the tests since this is likely a node issue that's been fixed by rebooting.

Summary by CodeRabbit

  • Tests
    • Enabled previously skipped DeepSeekV3Lite integration scenarios by removing skip waivers, ensuring these cases now run in CI.
    • Increases test coverage and validation across additional configurations, improving overall confidence in build quality.
    • No impact on product functionality, performance, or user experience.

Signed-off-by: Lanyu Liao <lancelly@users.noreply.github.com>
@coderabbitai

coderabbitai Bot commented Oct 8, 2025

Copy link
Copy Markdown
Contributor
📝 Walkthrough

Walkthrough

Removed two SKIP entries for DeepSeekV3Lite tests from tests/integration/test_lists/waives.txt, enabling those tests to run. No code or control-flow changes.

Changes

Cohort / File(s) Summary of Changes
Test waivers update
tests/integration/test_lists/waives.txt
Deleted two SKIP lines for TestDeepSeekV3Lite (ep4-mtp_nextn=2 and tp2pp2-fp8kv=False-attention_dp=True-cuda_graph=False-overlap_scheduler=True-torch_compile=False) in accuracy/test_llm_api_pytorch.py references.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description Check ⚠️ Warning The PR description omits the repository’s required template sections, including the structured “## Description,” “## Test Coverage,” and “## PR Checklist” headings, and does not provide a summary or test coverage details as outlined in the description template. Please update the PR description to include the mandated template headings and content by adding a concise summary, a detailed “## Description” of the change, a “## Test Coverage” section listing relevant tests, and ensure the “## PR Checklist” is addressed.
✅ Passed checks (2 passed)
Check name Status Explanation
Title Check ✅ Passed The title correctly follows the repository naming convention and clearly summarizes the key change of unwaiving tests previously skipped due to node issues after a reboot, making it concise and directly relevant to the changeset.
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.
✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e986165 and fe8ea31.

📒 Files selected for processing (1)
  • tests/integration/test_lists/waives.txt (0 hunks)
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
  • GitHub Check: Pre-commit Check

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

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

@lancelly

lancelly commented Oct 8, 2025

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #20772 [ run ] triggered by Bot

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #20772 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15700 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@chzblych
chzblych merged commit ed8e00a into NVIDIA:main Oct 9, 2025
7 checks passed
kris1025 pushed a commit to kris1025/TensorRT-LLM that referenced this pull request Oct 14, 2025
…er rebooting (NVIDIA#8193)

Signed-off-by: Lanyu Liao <lancelly@users.noreply.github.com>
Co-authored-by: Lanyu Liao <lancelly@users.noreply.github.com>
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.

3 participants