[None][test] Waive 10 failed cases for main in post-merge

[tensorrt-cicd]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 6274932, 6315645, 6322076, 6329052, 6344108

Waive entries added

full:A100/accuracy/test_disaggregated_serving.py::TestNemotron3Super120B::test_ctx_dp2_gen_tp4 SKIP (https://nvbugs/6344108)
full:A100/accuracy/test_disaggregated_serving.py::TestNemotron3Super120B::test_auto_dtype[mtp_nextn=3-block_reuse=True-use_py_transceiver=False] SKIP (https://nvbugs/6344108)
full:A100/accuracy/test_disaggregated_serving.py::TestNemotron3Super120B::test_auto_dtype[mtp_nextn=0-block_reuse=False-use_py_transceiver=True] SKIP (https://nvbugs/6322076)
full:A100/accuracy/test_disaggregated_serving.py::TestNemotron3Super120B::test_auto_dtype[mtp_nextn=0-block_reuse=False-use_py_transceiver=False] SKIP (https://nvbugs/6322076)
full:A100/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8[enable_block_reuse=False] SKIP (https://nvbugs/6315645)
full:A100/accuracy/test_llm_api_pytorch_multimodal.py::TestStep3_7::test_fp8_block_scales[mtp_nextn=3] SKIP (https://nvbugs/6274932)
full:A100/accuracy/test_llm_api_pytorch_multimodal.py::TestStep3_7::test_fp8_block_scales[mtp_nextn=0] SKIP (https://nvbugs/6274932)
full:A100/accuracy/test_llm_api_pytorch.py::TestStep3_7::test_fp8_block_scales[tp_size=4-ep_size=4-mtp_nextn=3] SKIP (https://nvbugs/6274932)
full:A100/accuracy/test_llm_api_pytorch.py::TestStep3_7::test_fp8_block_scales[tp_size=4-ep_size=4-mtp_nextn=0] SKIP (https://nvbugs/6274932)
full:A100/disaggregated/test_workers.py::test_workers_conditional_disaggregation_deepseek_v3_lite_bf16[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/6329052)

---

This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.

Summary by CodeRabbit

• Tests
  • Updated test waivers to enable A100 GPU configurations for model testing across multiple validation scenarios and hardware targets.
  • Added new test waivers for advanced model configurations, including automatic data type handling, multi-GPU parallelization, and distributed worker testing scenarios.

[xinhe-nv]

/bot skip --comment "only waive tests"

[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: e9429246-0436-4919-b025-0a9f7d392e83

📥 Commits

Reviewing files that changed from the base of the PR and between 683a70c and e15542f.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

Entries in tests/integration/test_lists/waives.txt are updated at lines 171–183: existing TestQwen3_5_35B_A3B bf16 waivers are changed to use the full:A100/ prefix, and new full:A100/ waivers are added for TestNemotron3Super120B, TestStep3_7 FP8 block-scale (including multimodal), and a DeepSeek V3 Lite conditional disaggregation worker test.

Changes

A100 Waiver Updates

Layer / File(s)	Summary
A100 waiver additions and prefix updates tests/integration/test_lists/waives.txt	Existing TestQwen3_5_35B_A3B bf16 waivers updated to include the full:A100/ prefix; new full:A100/ waivers added for TestNemotron3Super120B (auto-dtype, ctx_dp2_gen_tp4), TestStep3_7 FP8 block-scale and multimodal cases, and disaggregated/test_workers.py::test_workers_conditional_disaggregation_deepseek_v3_lite_bf16.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#15337: Also modifies waives.txt with overlapping TestQwen3_5_35B_A3B waiver entries.
• NVIDIA/TensorRT-LLM#15392: Adds waivers for the same TestQwen3_5_35B_A3B and TestStep3_7 FP8 block-scale tests under a different target prefix (full:H100/).
• NVIDIA/TensorRT-LLM#15389: Adds a SKIP waiver for the same test_workers_conditional_disaggregation_deepseek_v3_lite_bf16 test under full:L40S/.

Suggested reviewers

• jieli-matrix

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly describes the main change: waiving 10 failed test cases for the main branch in post-merge.
Description check	✅ Passed	The PR description is auto-generated and provides specific context: bug IDs, waive entries with test names, and appropriate links. However, it differs significantly from the template structure.
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.}

[tensorrt-cicd]

PR_Github #55167 [ skip ] triggered by Bot. Commit: e15542f Link to invocation

[tensorrt-cicd]

PR_Github #55167 [ skip ] completed with state SUCCESS. Commit: e15542f
Skipping testing for commit e15542f

Link to invocation