[https://nvbugs/6140408][chore] Unwaive DeepSeekV3Lite test_nvfp4_4gpus CUTLASS pp4 and CUTEDSL tp2pp2

[moraxu]

Dev Engineer Review

• Removed the obsolete NVBugs 6427411 waiver for the DeepSeekV3Lite NVFP4 4-GPU CUTEDSL tp2pp2 case.
• Added the corresponding CUTLASS pp4 waiver entry with fp8kv=False and Torch compile enabled.
• The change matches the stated test configurations and does not modify public entities or runtime code.
• The waiver list change has no apparent format or scope issues.

QA Engineer Review

• Only tests/integration/test_lists/waives.txt changed.
• Removed one DeepSeekV3Lite CUTEDSL tp2pp2 waiver.
• Added one DeepSeekV3Lite CUTLASS pp4 waiver.
• CBTS coverage data is not provided.

Verdict: needs follow-up

Description

Both cases were waived under https://nvbugs/6427411 (PP sampler regressions), which is fixed and closed. The CUTLASS pp4 case was verified at ToT (v1.3.0rc25) on 4x RTX PRO 6000 Blackwell (SM120): GSM8K 64.63 vs threshold 60.51 (reference 63.71). The CUTEDSL tp2pp2 case only runs on SM100/103 and is covered by GB200 post-merge.

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: 832a8843-e409-4c8c-a6dc-15de6bacd5d6

📥 Commits

Reviewing files that changed from the base of the PR and between 3d3d7c9 and c8084ac.

📒 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 integration waiver list replaces a DeepSeekV3Lite NVFP4 CUTEDSL configuration with a CUTLASS pp4 configuration that disables fp8kv and enables Torch compile.

Changes

Waiver configuration

Layer / File(s)	Summary
Update integration waiver entry tests/integration/test_lists/waives.txt	Replaces the waived tp2pp2 CUTEDSL entry with a pp4 CUTLASS entry using fp8kv=False and Torch compile. The skip status and bug reference remain.

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

Possibly related PRs

• NVIDIA/TensorRT-LLM#16637: Updates related DeepSeekV3Lite NVFP4 waiver configurations.
• NVIDIA/TensorRT-LLM#17542: Adjusts other integration test waivers in the same file.

Suggested labels: ci: full pre-merge approved

Suggested reviewers: bowenfu

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the NVBugs ticket, chore type, and the two test cases being unwaived.
Description check	✅ Passed	The description explains the waiver removal and verification details, but the Test Coverage section lacks an explicit test list.
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 💡 1

🛠️ Fix failing CI checks 💡

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[moraxu]

/bot run

[tensorrt-cicd]

PR_Github #65641 [ run ] triggered by Bot. Commit: c8084ac Link to invocation

[tensorrt-cicd]

PR_Github #65641 [ run ] completed with state FAILURE. Commit: c8084ac
/LLM/main/L0_MergeRequest_PR pipeline #53363 completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ 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

Link to invocation

[moraxu]

/bot run

[tensorrt-cicd]

PR_Github #65694 [ run ] triggered by Bot. Commit: c8084ac Link to invocation

[tensorrt-cicd]

PR_Github #65694 [ run ] completed with state SUCCESS. Commit: c8084ac
/LLM/main/L0_MergeRequest_PR pipeline #53411 completed with status: 'SUCCESS'

CI Report

Link to invocation