[None][test] Waive 8 failed cases for main in QA CI

[xinhe-nv]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 6184906, 6184914, 6190759

Waive entries added

test_e2e.py::test_openai_disagg_multi_nodes_completion[ctx_tp1pp2-gen_tp1pp2] SKIP (https://nvbugs/6190759)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_4gpus[pp4-mtp_nextn=0-fp8kv=False-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-sampler_async_worker=False] SKIP (https://nvbugs/6184914)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-pp4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-low_precision_combine=False-torch_compile=True] SKIP (https://nvbugs/6184914)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=2-pp4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-low_precision_combine=False-torch_compile=False] SKIP (https://nvbugs/6184914)
disaggregated/test_disaggregated.py::test_disaggregated_cuda_graph[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6184906)
disaggregated/test_disaggregated.py::test_disaggregated_conditional[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6184906)
disaggregated/test_disaggregated.py::test_disaggregated_single_gpu[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6184906)
disaggregated/test_disaggregated.py::test_disaggregated_kv_cache_time_output[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6184906)

---

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

Summary by CodeRabbit

• Tests
  • Updated integration test skip list with adjustments to existing entries and new test variants.

[crazydemo]

/bot run --stage-list ""

[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: 22e6bfb6-3c21-401f-a037-02e228b445e0

📥 Commits

Reviewing files that changed from the base of the PR and between 22bafe4 and fa0161d.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

Updates tests/integration/test_lists/waives.txt to skip additional integration test variants: DeepSeekV3Lite accuracy tests for fp8 block scales and fp4 quantization, disaggregated inference test scenarios for conditional execution and CUDA graphs, and an end-to-end disaggregated multi-node completion test.

Changes

Test Skip Waivers Update

Layer / File(s)	Summary
DeepSeekV3Lite accuracy test waivers tests/integration/test_lists/waives.txt	Adds new skip entry for TestDeepSeekV3Lite::test_fp8_block_scales_4gpus and replaces/updates TestDeepSeekV3Lite::test_nvfp4_4gpus waiver entries with additional parameter variants and updated bug references.
Disaggregated inference test waivers tests/integration/test_lists/waives.txt	Expands disaggregated test waiver blocks by adding test_disaggregated_conditional, test_disaggregated_cuda_graph, test_disaggregated_kv_cache_time_output, and test_disaggregated_single_gpu entries while re-listing existing ctxpp/ctxtp and perf-metrics parameterized waivers.
End-to-end disaggregated test waiver tests/integration/test_lists/waives.txt	Adds new skip entry for test_e2e.py::test_openai_disagg_multi_nodes_completion with specified parameter configuration and bug reference.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#13986: Both PRs update test waivers for TestDeepSeekV3Lite::test_nvfp4_4gpus and test_fp8_block_scales_4gpus in the same waiver list file with overlapping test entries.
• NVIDIA/TensorRT-LLM#14163: Both PRs modify tests/integration/test_lists/waives.txt to add and adjust integration-test SKIP entries across different test suites.
• NVIDIA/TensorRT-LLM#13204: Both PRs update tests/integration/test_lists/waives.txt by modifying SKIP entries for disaggregated/test_disaggregated.py with ctxpp-related variants.

Suggested reviewers

• jieli-matrix
• StanleySun639

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title follows the required template format [None][type] Summary and clearly indicates this is a waive PR for 8 failed test cases, matching the PR's primary purpose.
Description check	✅ Passed	The description is auto-generated and comprehensive, including bug references, specific waive entries, and all 8 test cases being skipped, though it doesn't follow the template's optional sections like Test Coverage and PR Checklist.
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.}

[tensorrt-cicd]

PR_Github #49196 [ run ] triggered by Bot. Commit: fa0161d Link to invocation

[tensorrt-cicd]

PR_Github #49196 [ run ] completed with state SUCCESS. Commit: fa0161d
/LLM/main/L0_MergeRequest_PR pipeline #38872 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[crazydemo]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #49311 [ reuse-pipeline ] triggered by Bot. Commit: fa0161d Link to invocation

[tensorrt-cicd]

PR_Github #49311 [ reuse-pipeline ] completed with state SUCCESS. Commit: fa0161d
Reusing PR_Github #49196 (Partly Tested) for commit fa0161d

Link to invocation