[None][test] Waive 15 failed cases for main in QA CI

[trtllm-agent]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 6714109, 6727262, 6728119, 6731978, 6732067, 6732110, 6732123

Waive entries added

full:B300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_vswa_reuse_4gpus[v2_kv_cache-one_model] SKIP (https://nvbugs/6732123)
full:B300/disaggregated/test_disaggregated.py::test_disaggregated_ctxpp4_gentp4[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6728119)
full:H100/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16[tp1-CUTLASS] SKIP (https://nvbugs/6732067)
full:GB300/test_e2e.py::test_multi_nodes_eval[Qwen3/saved_models_Qwen3-235B-A22B_nvfp4_hf-tp16-mmlu] SKIP (https://nvbugs/6732110)
full:H100/llmapi/test_llm_api_qa.py::TestLlmDefaultBackend::test_llm_args_type_default SKIP (https://nvbugs/6727262)
full:B300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_mxfp8_piecewise_cuda_graph[use_msa=False] SKIP (https://nvbugs/6714109)
full:GB300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_vswa_reuse_4gpus[v2_kv_cache-one_model] SKIP (https://nvbugs/6732123)
full:B200/accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[latency_moe_trtllm] SKIP (https://nvbugs/6731978)
full:B200/disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6728119)
full:B300/disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6728119)
full:GB300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_mxfp8_piecewise_cuda_graph[use_msa=False] SKIP (https://nvbugs/6714109)
full:L40S/disaggregated/test_disaggregated.py::test_disaggregated_ctxpp2_gentp2[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6728119)
full:L40S/disaggregated/test_disaggregated.py::test_disaggregated_multi_gpu[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6728119)
full:L40S/disaggregated/test_disaggregated.py::test_disaggregated_ctxtp2_genpp2[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6728119)
full:L40S/disaggregated/test_disaggregated.py::test_disaggregated_ctxpp2_genpp2[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6728119)

---

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

Dev Engineer Review

• Updated tests/integration/test_lists/waives.txt.
• Added 15 SKIP entries for B200, B300, GB300, H100, and L40S tests.
• The entries cover accuracy, disaggregated serving, end-to-end, and LLM API tests.
• Each entry references an NVIDIA bug.
• No public API or source-code changes were made.
• Review focus: confirm valid test paths, correct SKIP syntax, unique entries, and accurate bug references.

QA Engineer Review

• Modified tests/integration/test_lists/waives.txt.
• Added 15 GPU-specific waiver entries.
• Removed no entries.
• The changes are limited to test-list configuration.
• CBTS touchmap coverage is not applicable.
• Verdict: sufficient.

[jieli-matrix]

/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: d4cb319c-151d-4891-a690-b7be4baa866f

📥 Commits

Reviewing files that changed from the base of the PR and between 634a3ec and 251234a.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review.

---

Walkthrough

The integration waiver list adds NVIDIA bug-linked skip entries for GPU-specific accuracy, serving, end-to-end, and LLM API tests on B200, B300, GB300, H100, and L40S configurations.

Changes

GPU-specific test waivers

Layer / File(s)	Summary
Add GPU-specific waiver entries tests/integration/test_lists/waives.txt	Adds skip entries for affected B200, B300, GB300, H100, and L40S tests. Existing entries remain unchanged.

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

Merge Risk: ⚪ Minimal · up to 25123

This change skips 15 known failing GPU-specific integration cases with linked bug references. The waiver entries are valid and target existing tests, with no remaining merge-blocking risk identified.

Possibly related PRs

• NVIDIA/TensorRT-LLM#15195: Adds GPU-specific test waiver entries in the same waiver list.
• NVIDIA/TensorRT-LLM#17187: Adds GPU-specific waivers, including overlapping B300 cases.
• NVIDIA/TensorRT-LLM#18438: Adds NVIDIA bug-linked GPU-specific QA waivers.

Suggested reviewers: bowenfu, xinhe-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the change: waiving 15 failed QA CI cases on the main branch.
Description check	✅ Passed	The description explains the auto-generated waiver, target branch, bug references, and all 15 skipped test cases. It does not include explicit Test Coverage or PR Checklist sections, but the relevant …
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
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

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[tensorrt-cicd]

PR_Github #71847 [ skip ] triggered by Bot. Commit: 251234a Link to invocation

[tensorrt-cicd]

PR_Github #71847 [ skip ] completed with state SUCCESS. Commit: 251234a
Skipping testing for commit 251234a

Link to invocation