Skip to content

Conversation

lancelly
Copy link
Collaborator

@lancelly lancelly commented Sep 1, 2025

Re-enabled multiple previously skipped integration tests by removing waivers, expanding coverage across performance and accuracy scenarios for relevant model configurations. This enhances validation and release confidence without altering product behavior or interfaces. No new waivers were added; only deletions occurred. No changes to exported/public entities. End users should not see functional changes.

Summary by CodeRabbit

  • Tests
    • Re-enabled previously skipped DeepSeekR1 performance and accuracy tests for LLM API and GB200 full-path runs.
    • Restores coverage for FP8 blockscale and NVFP4 multi‑GPU scenarios across latency and throughput variants, improving validation across configurations.
    • No changes to product behavior, APIs, or user-facing functionality.

Signed-off-by: Lanyu Liao <[email protected]>
Signed-off-by: Lanyu Liao <[email protected]>
@lancelly lancelly changed the title [https://nvbugs/5445466][fix] unwaive DS R1 test cases with bug already fixed #7392 [https://nvbugs/5445466][fix] unwaive DS R1 test cases with bug already fixed Sep 1, 2025
@lancelly
Copy link
Collaborator Author

lancelly commented Sep 1, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

Copy link
Contributor

coderabbitai bot commented Sep 1, 2025

📝 Walkthrough

Walkthrough

Removes several SKIP entries from tests/integration/test_lists/waives.txt, re-enabling DeepSeekR1 tests for FP8 blockscale and NVFP4 multi-GPU throughput/latency variants, including GB200 full-path entries. No code or API changes.

Changes

Cohort / File(s) Summary
Test waiver updates (DeepSeekR1)
tests/integration/test_lists/waives.txt
Deleted SKIP lines for DeepSeekR1: FP8 blockscale [latency, throughput], NVFP4 multi_gpus [throughput_tp8, throughput, throughput_mtp]; also removed corresponding full:GB200/... entries. No additions.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

Suggested reviewers

  • litaotju
  • yiqingy0

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

💡 Knowledge Base configuration:

  • MCP integration is disabled by default for public repositories
  • Jira integration is disabled by default for public repositories
  • Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.

📥 Commits

Reviewing files that changed from the base of the PR and between 2b286ae and a36aca6.

📒 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
✨ Finishing Touches
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment

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
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR/Issue comments)

Type @coderabbitai help to get the list of available commands.

Other keywords and placeholders

  • Add @coderabbitai ignore or @coderabbit ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

Status, Documentation and Community

  • Visit our Status Page to check the current availability of CodeRabbit.
  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17177 [ run ] triggered by Bot

Signed-off-by: Lanyu Liao <[email protected]>
@lancelly
Copy link
Collaborator Author

lancelly commented Sep 1, 2025

/bot kill

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 1, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17177 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #12913 completed with status: 'FAILURE'

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 1, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17220 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17220 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #12948 completed with status: 'FAILURE'

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 2, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 5, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17764 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17764 [ run ] completed with state DISABLED
L0 testing is limited to prioritized users. User lancelly is not in the prioritized list. L0 testing cannot be triggered.

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 8, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17968 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17968 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13467 completed with status: 'FAILURE'

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 8, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17997 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #17997 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13488 completed with status: 'FAILURE'

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 9, 2025

/bot run --add-multi-gpu-test --disable-fail-fast

@lancelly
Copy link
Collaborator Author

lancelly commented Sep 9, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18170 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18170 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13616 completed with status: 'SUCCESS'

Signed-off-by: Lanyu Liao <[email protected]>
Signed-off-by: Lanyu Liao <[email protected]>
@litaotju
Copy link
Collaborator

litaotju commented Sep 9, 2025

skip merge since only a trivial resolve is done.

@litaotju
Copy link
Collaborator

litaotju commented Sep 9, 2025

/bot skip --comment "skip since a full pipeline passed"

@litaotju litaotju merged commit af40384 into NVIDIA:main Sep 9, 2025
4 of 5 checks passed
@tensorrt-cicd
Copy link
Collaborator

PR_Github #18205 [ ] completed with state FAILURE
Not allowed on merged PR

gergely-magyar pushed a commit to gergely-magyar/TensorRT-LLM that referenced this pull request Sep 9, 2025
…dy fixed (NVIDIA#7429)

Signed-off-by: Lanyu Liao <[email protected]>
Co-authored-by: Lanyu Liao <[email protected]>
Signed-off-by: Gergely Magyar <[email protected]>
Wong4j pushed a commit to Wong4j/TensorRT-LLM that referenced this pull request Sep 20, 2025
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