[None][test] Waive 11 failed cases for main in QA CI

[tensorrt-cicd]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_FUNCTION_CLUSTER_TEST/1555/
Bug(s): 6316980, 6316981, 6317600, 6329165, 6331421, 6344883, 6344884

Waive entries added

full:GB300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache_no_reuse-tp4-trtllm-fp8] SKIP (https://nvbugs/6316980)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[nvfp4_ws4_80gb-trtllm] SKIP (https://nvbugs/6316981)
full:GB300/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8_moe_dflash SKIP (https://nvbugs/6317600)
full:GB300/accuracy/test_llm_api_pytorch.py::TestQwen3_5_4B::test_dflash SKIP (https://nvbugs/6344883)
full:GB300/disaggregated/test_auto_scaling.py::test_worker_restart[http-round_robin] SKIP (https://nvbugs/6344884)
full:GB300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-trtllm-fp8] SKIP (https://nvbugs/6316980)
full:GB300/accuracy/test_llm_api_pytorch.py::TestQwen3_5_397B_A17B::test_nvfp4[tep4_trtllm] SKIP (https://nvbugs/6317600)
full:GB300/accuracy/test_llm_api_pytorch_multimodal.py::TestQwen2_5_VL_7B::test_auto_dtype SKIP (https://nvbugs/6331421)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[bf16_ws4_180gb-trtllm] SKIP (https://nvbugs/6316981)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[nvfp4-1-attn_dp_off-trtllm] SKIP (https://nvbugs/6329165)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[fp8_ws4_80gb-trtllm] SKIP (https://nvbugs/6316981)

---

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

Summary by CodeRabbit

Release Notes

This release contains internal testing infrastructure updates only. No user-facing features, bug fixes, or changes have been introduced.

[coderabbitai]

📝 Walkthrough

Walkthrough

Adds 11 new SKIP waiver lines to tests/integration/test_lists/waives.txt in the GB300 section (lines 209–226) for failing tests across test_llm_api_autodeploy.py, test_llm_api_pytorch.py, test_llm_api_pytorch_multimodal.py, and disaggregated/test_auto_scaling.py, with at least one updated nvbugs reference.

Changes

GB300 Waiver Additions

Layer / File(s)	Summary
GB300 waiver entries tests/integration/test_lists/waives.txt	Adds SKIP waivers for TestNemotronSuperV3::test_mtp (bf16/fp8/nvfp4 trtllm configs), TestGPTOSS::test_w4_4gpus (v2_kv_cache ep4/tp4 fp8), TestQwen3_5_35B_A3B::test_fp8_moe_dflash (updated nvbugs ref), TestQwen3_5_397B_A17B::test_nvfp4[tep4_trtllm], TestQwen3_5_4B::test_dflash, TestQwen2_5_VL_7B::test_auto_dtype (updated nvbugs ref), and test_worker_restart[http-round_robin].

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#15337: Modifies the same waives.txt file and adds overlapping TestGPTOSS::test_w4_4gpus waivers with similar kv-cache and parallelism parameter variants.
• NVIDIA/TensorRT-LLM#15341: Modifies the same waives.txt to add/update the waiver for TestQwen2_5_VL_7B::test_auto_dtype with nvbugs reference updates.
• NVIDIA/TensorRT-LLM#15342: Modifies the same waives.txt to add/adjust SKIP waivers for TestQwen3_5_35B_A3B::test_fp8_moe_dflash and TestQwen2_5_VL_7B::test_auto_dtype.

Suggested reviewers

• crazydemo
• jieli-matrix
• StanleySun639
• LarryXFly
• xinhe-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: waiving 11 failed test cases for the main branch in QA CI.
Description check	✅ Passed	The PR description is auto-generated and provides context, bug references, and a clear list of waived entries, though it deviates 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.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@tests/integration/test_lists/waives.txt`:
- Around line 209-226: Remove all duplicate waive entries in the waives.txt file
where the same test nodeid and nvbug reference appear multiple times.
Specifically, remove one instance of each duplicate pair:
TestNemotronNanoV3::test_accuracy[nvfp4-1-attn_dp_off-trtllm],
TestNemotronSuperV3::test_mtp[bf16_ws4_180gb-trtllm],
TestNemotronSuperV3::test_mtp[fp8_ws4_80gb-trtllm],
TestNemotronSuperV3::test_mtp[nvfp4_ws4_80gb-trtllm],
TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-trtllm-fp8], and
TestGPTOSS::test_w4_4gpus[v2_kv_cache_no_reuse-tp4-trtllm-fp8]. Additionally,
consolidate entries that have the same test nodeid but different nvbug
references by keeping only one entry with the most recent or correct nvbug
reference. For TestQwen3_5_35B_A3B::test_fp8_moe_dflash and
TestQwen2_5_VL_7B::test_auto_dtype, determine which nvbug reference is correct
and remove the redundant entry. Ensure the file maintains one entry per unique
test nodeid to pass the waive list check.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 278b275a-95e2-48d8-baa0-c2d4666da041

📥 Commits

Reviewing files that changed from the base of the PR and between 3448424 and 45c069e.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[xinhe-nv]

/bot skip --comment "Only waive tests"

[tensorrt-cicd]

PR_Github #55145 [ skip ] triggered by Bot. Commit: 90630de Link to invocation

[tensorrt-cicd]

PR_Github #55145 [ skip ] completed with state SUCCESS. Commit: 90630de
Skipping testing for commit 90630de

Link to invocation