[https://nvbugs/6428096][fix] Unwaive DeepSeekV3Lite compiled tp2pp2

[cascade812]

…test

Dev Engineer Review

• Removed the waiver for the compiled DeepSeekV3Lite tp2pp2 BF16 4-GPU test with torch_compile=True and CUDA graphs disabled.
• Removed the associated NVBUG 6428096 reference.
• The change is limited to tests/integration/test_lists/waives.txt and does not alter public entities.

QA Engineer Review

• No test-db/ or qa/ files were modified.
• Removed one entry from tests/integration/test_lists/waives.txt.
• The test is now expected to run in the compiled tp2pp2 configuration.
• Verdict: needs follow-up because CBTS coverage data is unavailable.

Description

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.

[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: 6f632bc4-242c-4eac-80a8-a6a66c7b28be

📥 Commits

Reviewing files that changed from the base of the PR and between f12c5e5 and 4aeb4e5.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

• tests/integration/test_lists/waives.txt

---

Walkthrough

The change removes one skip configuration from the integration test waiver list. The affected test uses DeepSeekV3Lite BF16 on four GPUs with tp2pp2, torch_compile=True, and cuda_graph=False.

Changes

DeepSeekV3Lite waiver removal

Layer / File(s)	Summary
Remove test waiver tests/integration/test_lists/waives.txt	Removes the skip entry for the specified DeepSeekV3Lite BF16 4-GPU test configuration.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#17155: Removes a waiver for another DeepSeekV3Lite tp2pp2 BF16 4-GPU configuration.
• NVIDIA/TensorRT-LLM#17340: Adjusts DeepSeekV3Lite test waiver entries in the same file.
• NVIDIA/TensorRT-LLM#17301: Removes a separate DeepSeekV3Lite skip entry from the same waiver list.

Suggested reviewers: brnguyen2, qijune

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description leaves the required Description and Test Coverage sections empty and does not explain the issue, solution, or relevant tests.	Add a concise issue and solution summary, identify the relevant test coverage, and complete the applicable checklist items.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title follows the required ticket and type format and clearly describes unwaiving the DeepSeekV3Lite compiled tp2pp2 test.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[cascade812]

/bot run --stage-list "DGX_H200-4_GPUs-PyTorch-Post-Merge-1"

[brnguyen2]

Approving — the comments below are optional touch-ups, not blockers.

Removal looks justified — the tracked failure and the follow-on issue found while investigating it are both resolved on main.

One thing before merge: this parametrization only appears in post_merge blocks (l0_gb200_multi_gpus.yml:111, l0_dgx_b300.yml:37, l0_rtx_pro_6000.yml:76), so a plain /bot run won't exercise it and the unwaive ships unvalidated. Please run the stage explicitly, e.g. /bot run --extra-stage "GB200-4_GPUs-PyTorch-Post-Merge-1", and link the result. The test was flagged flaky historically, so one green run is the minimum evidence.

[cascade812]

/bot run --extra-stage "GB200-4_GPUs-PyTorch-Post-Merge-1"

[tensorrt-cicd]

PR_Github #64415 [ run ] triggered by Bot. Commit: 4aeb4e5 Link to invocation

[tensorrt-cicd]

PR_Github #64415 [ run ] completed with state FAILURE. Commit: 4aeb4e5
/LLM/main/L0_MergeRequest_PR pipeline #52297 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