[https://nvbugs/6272573][ci] Unwaive skipped test

[2ez4bz]

Summary by CodeRabbit

• Chores

  • Updated test infrastructure configuration for DGX_B200-PyTorch platform.

• Tests

  • Removed test waiver for a multimodal encoder validation test.

Description

The original issue was likely related to us temporarily switching to
a different B200 cluster for CI during the maintenance window of
our regular cluster.

Test Coverage

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)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• 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.

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #52835 [ run ] triggered by Bot. Commit: 5926ecd Link to invocation

[tensorrt-cicd]

PR_Github #52835 [ run ] completed with state SUCCESS. Commit: 5926ecd
/LLM/main/L0_MergeRequest_PR pipeline #42088 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

CI Agent Failure Analysis

Link to invocation

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #52891 [ run ] triggered by Bot. Commit: 5926ecd Link to invocation

[tensorrt-cicd]

PR_Github #52891 [ run ] completed with state SUCCESS. Commit: 5926ecd
/LLM/main/L0_MergeRequest_PR pipeline #42141 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

CI Agent Failure Analysis

Link to invocation

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 9f02f15d-69ee-4910-99eb-d0c4bc4e8d2f

📥 Commits

Reviewing files that changed from the base of the PR and between 48d2b89 and 43d2497.

📒 Files selected for processing (2)

• jenkins/L0_Test.groovy
• tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This PR updates test infrastructure for DGX_B200-PyTorch: the SLURM stage mapping now uses 9 splits instead of 7, with stages 8 and 9 added and split counts updated across all entries. A multimodal encoder test waiver was removed from the skip list.

Changes

Test Infrastructure Configuration

Layer / File(s)	Summary
DGX_B200-PyTorch SLURM split count increase jenkins/L0_Test.groovy	The SLURM stage configuration for DGX_B200-PyTorch is updated from 7 to 9 total test splits. Split entries for IDs 1–7 are updated with split_count set to 9, and new stage entries for split IDs 8 and 9 are added.
Test waiver removal tests/integration/test_lists/waives.txt	A single waiver entry for test_single_request_chat_multiple_images[pd_disagg-qwen3_30b_a3b_fp8] is removed, allowing that test to run without being skipped.

Possibly related PRs

• NVIDIA/TensorRT-LLM#14661: Updates SLURM stage mapping for DGX_B200-PyTorch by adjusting split IDs and split_count values.
• NVIDIA/TensorRT-LLM#14948: Removes a waiver entry from tests/integration/test_lists/waives.txt.
• NVIDIA/TensorRT-LLM#15078: Removes a skipped-test waiver entry from tests/integration/test_lists/waives.txt.

Suggested reviewers

• yuanjingx87
• dpitman-nvda
• ZhanruiSunCh

---

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description lacks critical details about what was changed and why. The Test Coverage section is empty, and the explanation only mentions a temporary cluster switch without explaining the actual code changes.	Add a clear explanation of what changes were made to the waives.txt and jenkins/L0_Test.groovy files, and include relevant test cases or justification for removing the waiver.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title references a bug ticket and describes the main change (unwaiving a skipped test), which aligns with the actual modifications to the waives.txt file.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ 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.}

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #53143 [ run ] triggered by Bot. Commit: 43d2497 Link to invocation

[tensorrt-cicd]

PR_Github #53143 [ run ] completed with state FAILURE. Commit: 43d2497
/LLM/main/L0_MergeRequest_PR pipeline #42347 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

CI Agent Failure Analysis

Link to invocation

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #53221 [ run ] triggered by Bot. Commit: 43d2497 Link to invocation

[tensorrt-cicd]

PR_Github #53221 [ run ] completed with state SUCCESS. Commit: 43d2497
/LLM/main/L0_MergeRequest_PR pipeline #42416 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation