[nvbug/5410296][fix] Fix OOM in Llama 4 disagg-serve tests

[bo-nv]

Summary by CodeRabbit

• Tests
  • Updated test configurations to limit maximum sequence length to 8192 tokens, enhancing stability in continuous integration.
  • Removed a skip decorator from a specific test, enabling broader test execution.
  • Removed two skip entries, allowing additional tests to run in the standard test suite.

Description

1. Limit the max_seq_len to 8192 to fix the OOM issue according to https://github.com/NVIDIA/TensorRT-LLM/pull/5735/files
2. Unwaive test_disaggregated_deepseek_v3_lite_fp8_nixl on B200

[coderabbitai]

📝 Walkthrough

Walkthrough

This change updates the configuration for a disaggregated serving accuracy test to explicitly set a maximum sequence length, removes a decorator from a disaggregated test, and deletes two skip entries from the test waiver list. No changes to logic, control flow, or public interfaces are present.

Changes

Cohort / File(s)	Change Summary
Accuracy Test Config Update tests/integration/defs/accuracy/test_disaggregated_serving.py	Added "max_seq_len": 8192 to both ctx_server_config and gen_server_config in test_auto_dtype to limit sequence length and prevent OOM during CI warmup.
Decorator Removal tests/integration/defs/disaggregated/test_disaggregated.py	Removed the @skip_no_hopper decorator from test_disaggregated_deepseek_v3_lite_fp8_nixl.
Test Waiver List Update tests/integration/test_lists/waives.txt	Removed two skip entries for accuracy/test_disaggregated_serving.py::TestLlama4ScoutInstruct::test_auto_dtype with [False] and [True] parameters.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~7 minutes

Possibly related PRs

• [TRTLLM-6471] Infra: unwaive nixl tests and some disagg-serve tests #6095: Re-enables some disaggregated serving tests and modifies related skip lists, overlapping with the same test management areas as this PR.
• [Infra] - Wiave failed tests in post-merge #6331: Adds skip entries for the same test that this PR now removes, indicating direct relation in skip list management.
• test: [CI] remove closed bugs #6201: Removes skip entries from the waiver list for the same test, similar to this PR's changes but with a narrower scope.

Suggested reviewers

• litaotju
• venkywonka
• yuxianq

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.

---

📜 Recent review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between f53e20d and b1c01cd.

📒 Files selected for processing (3)

• tests/integration/defs/accuracy/test_disaggregated_serving.py (1 hunks)
• tests/integration/defs/disaggregated/test_disaggregated.py (0 hunks)
• tests/integration/test_lists/waives.txt (0 hunks)

💤 Files with no reviewable changes (2)

• tests/integration/test_lists/waives.txt
• tests/integration/defs/disaggregated/test_disaggregated.py

🚧 Files skipped from review as they are similar to previous changes (1)

• tests/integration/defs/accuracy/test_disaggregated_serving.py

⏰ 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 Docstrings

🧪 Generate unit tests

• Create PR with unit tests
• Post copyable unit tests in a comment

---

🪧 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.
  • Explain this complex logic.
  • 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. Examples:
  • @coderabbitai explain this code block.
  • @coderabbitai modularize this function.
• 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 src/utils.ts and explain its main purpose.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Support

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

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai generate unit tests to generate unit tests for this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai 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.

Documentation and Community

• 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.

[bo-nv]

/bot run --add-multi-gpu-test

[tensorrt-cicd]

PR_Github #13327 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #13327 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9961 completed with status: 'FAILURE'

[bo-nv]

/bot run --add-multi-gpu-test

[tensorrt-cicd]

PR_Github #13344 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #13344 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9975 completed with status: 'FAILURE'

[bo-nv]

/bot run --add-multi-gpu-test

[tensorrt-cicd]

PR_Github #13387 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #13387 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10013 completed with status: 'FAILURE'

[bo-nv]

/bot run --add-multi-gpu-test

[tensorrt-cicd]

PR_Github #13448 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #13448 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10064 completed with status: 'SUCCESS'