[https://nvbugs/5455140][fix] unwaive tests related to GB200 OOM #8159

lancelly · 2025-10-06T16:23:21Z

We suspected the OOM in one of these tests was due to a cluster misconfiguration. Now that it's fixed, we have re-enabled the related tests to see if the OOM is resolved.

Summary by CodeRabbit

Tests
- Re-enabled a previously skipped integration test, improving overall test coverage and CI reliability.
- Restores automated verification for an important performance path, helping catch regressions earlier and provide faster release feedback.
- No changes to product features, performance, or user experience.

Signed-off-by: Lanyu Liao <[email protected]>

coderabbitai · 2025-10-06T16:26:11Z

📝 Walkthrough

Walkthrough

A single change was made to tests/integration/test_lists/waives.txt, removing one skip entry to unskip a specific test case. No other files or lines were modified.

Changes

Cohort / File(s)	Summary of Changes
Test waiver list update `tests/integration/test_lists/waives.txt`	Removed skip entry for `accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_trtllmgen]`, unskipping the test.

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 pull request description does not follow the repository’s required template because it omits the summary annotation and the mandatory “## Description”, “## Test Coverage”, and “## PR Checklist” sections, leaving the template structure incomplete.	Please update the PR description to include the template header (e.g., @coderabbitai summary), a “## Description” section explaining the change, a “## Test Coverage” section listing relevant tests, and the “## PR Checklist” to ensure compliance with repository standards.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changes. Docstring coverage check skipped.
Title Check	✅ Passed	The pull request title succinctly describes the main change of re-enabling tests related to a GB200 OOM issue and references the relevant bug and fix context, making it clear to reviewers.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

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

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

lancelly · 2025-10-06T16:30:49Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-06T16:36:36Z

PR_Github #20680 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-06T20:03:56Z

PR_Github #20680 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15623 completed with status: 'FAILURE'

lancelly · 2025-10-07T01:45:30Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-07T01:51:25Z

PR_Github #20695 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-07T04:01:32Z

PR_Github #20695 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15633 completed with status: 'FAILURE'

lancelly · 2025-10-07T04:05:11Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-07T04:10:35Z

PR_Github #20707 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-07T05:53:40Z

PR_Github #20707 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #15644 completed with status: 'FAILURE'

lancelly · 2025-10-07T06:32:03Z

/bot run

tensorrt-cicd · 2025-10-07T06:37:18Z

PR_Github #20714 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-07T07:08:48Z

PR_Github #20714 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #15650 completed with status: 'FAILURE'

lancelly · 2025-10-07T07:12:43Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-07T07:17:58Z

PR_Github #20715 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-07T08:55:43Z

PR_Github #20715 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15651 completed with status: 'FAILURE'

lancelly · 2025-10-07T09:08:04Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-07T09:13:26Z

PR_Github #20724 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-07T10:54:42Z

PR_Github #20724 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15659 completed with status: 'FAILURE'

lancelly · 2025-10-07T10:57:55Z

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

lancelly · 2025-10-07T13:23:33Z

/bot run --disable-fail-fast

lancelly · 2025-10-07T15:32:13Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-07T15:37:53Z

PR_Github #20737 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-07T17:23:07Z

PR_Github #20737 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15670 completed with status: 'FAILURE'

lancelly · 2025-10-08T01:34:46Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-08T01:41:13Z

PR_Github #20757 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-08T04:50:25Z

PR_Github #20757 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15687 completed with status: 'SUCCESS'

…DIA#8159) Signed-off-by: Lanyu Liao <[email protected]> Co-authored-by: Lanyu Liao <[email protected]>

unwaive tests

88596e0

Signed-off-by: Lanyu Liao <[email protected]>

Merge branch 'main' into unwaive_oom_tests

806c73f

chzblych approved these changes Oct 8, 2025

View reviewed changes

chzblych merged commit d57b8f0 into NVIDIA:main Oct 8, 2025
5 checks passed

[https://nvbugs/5455140][fix] unwaive tests related to GB200 OOM #8159

[https://nvbugs/5455140][fix] unwaive tests related to GB200 OOM #8159

Uh oh!

Conversation

lancelly commented Oct 6, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Oct 6, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

lancelly commented Oct 6, 2025

Uh oh!

tensorrt-cicd commented Oct 6, 2025

Uh oh!

tensorrt-cicd commented Oct 6, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

lancelly commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

tensorrt-cicd commented Oct 7, 2025

Uh oh!

lancelly commented Oct 8, 2025

Uh oh!

tensorrt-cicd commented Oct 8, 2025

Uh oh!

tensorrt-cicd commented Oct 8, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

lancelly commented Oct 6, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Oct 6, 2025 •

edited

Loading