[None][infra] Waive 13 failed cases for main in post-merge 2722

[ZhanruiSunCh]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by @mzweilz)
Target branch: main
Bug(s): 6185190, 6185192, 6185196, 6185212

Waive entries added

accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_dsa_host_cache_offload[host_cache_offload] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_dsa_host_cache_offload[host_cache_offload_mtp1] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_dsa_host_cache_offload[host_cache_offload_mtp3_no_adp] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[latency_default] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline_mtp1] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus_piecewise_cuda_graph[baseline] SKIP (https://nvbugs/6185196)
examples/test_visual_gen.py::test_vbench_dimension_score_wan22_a14b_fp8 SKIP (https://nvbugs/6185192)
test_doc.py::test_url_validity SKIP (https://nvbugs/6185190)
unittest/_torch/modules/moe/test_moe_module.py::test_configurable_moe_multi_gpu[parallel=DEP-comm=NVLINK_ONE_SIDED-e256_k8_h7168_i2048-seq=8-dtype=torch.bfloat16-backend=CUTLASS-quant=W8A16-routing=Renormalize] SKIP (https://nvbugs/6185212)
unittest/_torch/modules/moe/test_moe_module.py::test_configurable_moe_multi_gpu[parallel=DEP-comm=NVLINK_ONE_SIDED-e256_k8_h7168_i2048-seq=8-dtype=torch.bfloat16-backend=TRTLLM-quant=FP8_BLOCK_SCALES-routing=Renormalize] SKIP (https://nvbugs/6185212)
unittest/_torch/modules/moe/test_moe_module.py::test_configurable_moe_multi_gpu[parallel=DEP-comm=NVLINK_ONE_SIDED-e256_k8_h7168_i2048-seq=8-dtype=torch.bfloat16-backend=TRTLLM-quant=W4A16_MXFP4-routing=Renormalize] SKIP (https://nvbugs/6185212)

---

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

Summary by CodeRabbit

• Tests
  • Updated test skip list to manage integration test waivers for various system configurations and features.

[mzweilz]

/bot skip --comment "Waive PR for post merge created via CI report, skip testing"

[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: ebb01978-4e61-491b-9e7a-52ac3b24d0a6

📥 Commits

Reviewing files that changed from the base of the PR and between 13bbeb9 and 2b44622.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This PR updates tests/integration/test_lists/waives.txt to revise and expand the set of integration tests marked SKIP. Changes include replacing DeepSeekV32 FP8 blockscale waivers with broader accuracy test waivers, adding visual generation and documentation test skip markers, and introducing MOE module multi-GPU test configuration waivers.

Changes

Test Skip Waivers

Layer / File(s)	Summary
DeepSeekV32 and NVFP4 accuracy test waivers tests/integration/test_lists/waives.txt	Expands DeepSeekV32 test waivers to include host-cache offload, multiple FP8 blockscale variants, and NVFP4 multi-GPU execution modes (single and piecewise CUDA graph).
Example and documentation test waivers tests/integration/test_lists/waives.txt	Adds skip waivers for visual generation benchmark dimension scoring and documentation URL validity tests.
MOE module multi-GPU test waivers tests/integration/test_lists/waives.txt	Introduces three new skip waivers for configurable MOE multi-GPU tests with different NVLINK communication and quantization/routing backend combinations.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14119: Updates the same waiver list with skip entries for unittest/_torch/modules/moe/test_moe_module.py configurable multi-GPU test cases with different comm/backend/quantization routing configurations.
• NVIDIA/TensorRT-LLM#14169: Modifies the same waiver list file (tests/integration/test_lists/waives.txt) with revisions and extensions to SKIP waivers for DeepSeekV32 and related test entries.
• NVIDIA/TensorRT-LLM#14034: Modifies the same tests/integration/test_lists/waives.txt file to adjust SKIP waiver entries for different integration test targets.

Suggested reviewers

• mzweilz
• jieli-matrix
• niukuo

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is missing critical sections from the template: no explicit 'Description' section explaining the issue/solution, no 'Test Coverage' section, and the PR Checklist is not completed. While the auto-generated content provides waive entries and context, it does not follow the required template structure.	Add a proper 'Description' section explaining the waive purpose, include a 'Test Coverage' section, and complete the PR Checklist as specified in the repository template.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies this as an infrastructure change to waive 13 failed test cases, with the specific post-merge number and target branch context provided.
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 #48817 [ skip ] triggered by Bot. Commit: 2b44622 Link to invocation

[tensorrt-cicd]

PR_Github #48817 [ skip ] completed with state SUCCESS. Commit: 2b44622
Skipping testing for commit 2b44622

Link to invocation