[https://nvbugs/6517844][test] Unwaive DeepSeek V3 Lite RTX Pro 6000D test

[nv-lschneider]

FIx merged with #16956
This just unwaives the test.

Dev Engineer Review

• Removed the waiver for TestDeepSeekV3Lite::test_bfloat16_4gpus with ep4, mtp_nextn=2, and torch_compile=False.
• The change is limited to tests/integration/test_lists/waives.txt.
• The waiver removal is consistent with the objective to re-enable the test for RTX Pro 6000D GPUs.
• No code, API, performance, or error-handling changes were made.

QA Engineer Review

• Modified tests/integration/test_lists/waives.txt.
• Removed the waiver entry for TestDeepSeekV3Lite::test_bfloat16_4gpus.
• No test code changed.
• CBTS coverage data is unavailable. Verdict: needs follow-up.
• Run the requested RTXPro6000D-4_GPUs-PyTorch-Post-Merge-* bot test stages.

• Please check this after reviewing the above items as appropriate for this PR.

[nv-lschneider]

/bot run --stage-list "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-*"

[coderabbitai]

Walkthrough

Removed the waiver for TestDeepSeekV3Lite::test_bfloat16_4gpus with ep4, mtp_nextn=2, and torch_compile=False.

Changes

Cohort / File(s)	Summary
Test waiver cleanup tests/integration/test_lists/waives.txt	Removes the waiver associated with NVBugs issue 6517844.

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

Possibly related PRs

• NVIDIA/TensorRT-LLM#17294: Removes a different test waiver from the same waiver list.
• NVIDIA/TensorRT-LLM#17309: Removes skipped test waivers from the same waiver list.
• NVIDIA/TensorRT-LLM#17349: Updates test waiver entries in the same waiver list.

Suggested reviewers: brnguyen2, stanleysun639, tburt-nv

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description states the change but omits the required Description and Test Coverage sections and provides no specific test details.	Add the required Description and Test Coverage sections, and identify the relevant RTX Pro 6000D test stages or validation results.

✅ Passed checks (4 passed)

Check name	Status	Explanation
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.
Title check	✅ Passed	The title clearly identifies the NVBugs issue and the primary change: unwaiving the DeepSeek V3 Lite RTX Pro 6000D test.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[tensorrt-cicd]

PR_Github #64343 [ run ] triggered by Bot. Commit: 7f642ef Link to invocation

[tensorrt-cicd]

PR_Github #64343 [ run ] completed with state FAILURE. Commit: 7f642ef
/LLM/main/L0_MergeRequest_PR pipeline #52239 (Partly Tested) 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

[nv-lschneider]

/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-*"

[tensorrt-cicd]

PR_Github #64356 [ run ] triggered by Bot. Commit: 7f642ef Link to invocation

[tensorrt-cicd]

PR_Github #64356 [ run ] completed with state SUCCESS. Commit: 7f642ef
/LLM/main/L0_MergeRequest_PR pipeline #52250 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

[brnguyen2]

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

Matches the bug — the fix in #16956 landed and the bug asks for exactly this unwaive.

Two CI notes before merging:

• The test only runs post-merge, so a plain /bot run won't cover it. Run /bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" — it failed in both stages, not just -2.
• The removed line has no GPU prefix, so it was skipping this parametrization on B200/B300/GB300 too (l0_dgx_b200.yml, l0_dgx_b300.yml, l0_gb300_multi_gpus.yml). Worth adding those multi-GPU post-merge stages as well so the re-enable doesn't turn into a post-merge surprise on a platform nobody checked.

[nv-lschneider]

/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1,RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2,DGX_B300-4_GPUs-PyTorch-Post-Merge-1,DGX_B300-4_GPUs-PyTorch-Post-Merge-2,GB300-4_GPUs-PyTorch-Post-Merge-1,GB300-4_GPUs-PyTorch-Post-Merge-2,GB300-4_GPUs-PyTorch-Post-Merge-3"

[nv-lschneider]

Thanks for the review, I am broadening the CI coverage to get full coverage.
Thanks for the detailed reply.