[None][test] Waive 3 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_TEST/2242/
Bug(s): 6313060, 6313072, 6313076

Waive entries added

full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6313060)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True-enable_chunked_prefill=False-v2_kv_cache=False] SKIP (https://nvbugs/6313072)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8[enable_block_reuse=False] SKIP (https://nvbugs/6313076)

---

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

Summary by CodeRabbit

• Tests
  • Added test waivers for specific model variants (DeepSeekV3Lite and Qwen 3.5 35B) on Blackwell RTX_PRO_6000 hardware with various optimization settings to handle known test conditions.

[jieli-matrix]

close as triage with a new PR

[jieli-matrix]

/bot run --stage-list ""

[coderabbitai]

📝 Walkthrough

Walkthrough

Added three test waiver entries to skip integration tests on RTX_PRO_6000 Blackwell hardware: two DeepSeekV3Lite bfloat16 configurations with different parameter combinations and one Qwen3_5_35B_A3B fp8 configuration, each linked to specific NVBUG references.

Changes

RTX_PRO_6000 Blackwell Test Waivers

Layer / File(s)	Summary
RTX_PRO_6000 Blackwell test waivers tests/integration/test_lists/waives.txt	Added two DeepSeekV3Lite bfloat16 SKIP waivers with mtp_nextn=0 and differing v2_kv_cache/torch_compile configurations, and one Qwen3_5_35B_A3B fp8 waiver with enable_block_reuse=False, all for RTX_PRO_6000 Blackwell tied to NVBUG references.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#13790: Directly related waiver-list update with similar SKIP/waive entries tied to NVBUG references.
• NVIDIA/TensorRT-LLM#15253: Modifies the same waiver file for Blackwell-related test failures with NVBUG-linked entries.
• NVIDIA/TensorRT-LLM#15326: Adds DeepSeekV3Lite bfloat16 waivers to the same waiver list with overlapping test-case coverage.

Suggested reviewers

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

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The description provides clear context about the auto-generated PR, including Jenkins build reference and three bug references, but omits required sections from the template.	While the auto-generated format is acceptable, consider adding a brief 'Description' section explaining the waiver rationale and a 'Test Coverage' section noting which tests are waived.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically summarizes the main change: waiving 3 failed test cases for the main branch in QA CI.
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.}

[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 224-225: The waiver's bug ID is incorrect: update the first
DeepSeek waiver reference from 6313072 to 6313060 so it matches the PR
assignment; specifically edit the entry for
TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=True]
to use 6313060 instead of 6313072.

🪄 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: 6b679010-da51-4d03-8dce-892439586087

📥 Commits

Reviewing files that changed from the base of the PR and between bb32597 and 2b56fb5.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[tensorrt-cicd]

PR_Github #54037 [ run ] triggered by Bot. Commit: 2b56fb5 Link to invocation

[tensorrt-cicd]

PR_Github #54037 [ run ] completed with state SUCCESS. Commit: 2b56fb5
/LLM/main/L0_MergeRequest_PR pipeline #43121 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54247 [ run ] triggered by Bot. Commit: 8ab7019 Link to invocation

[tensorrt-cicd]

PR_Github #54247 [ run ] completed with state SUCCESS. Commit: 8ab7019
/LLM/main/L0_MergeRequest_PR pipeline #43321 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54409 [ run ] triggered by Bot. Commit: 44b0b39 Link to invocation

[tensorrt-cicd]

PR_Github #54409 [ run ] completed with state FAILURE. Commit: 44b0b39
/LLM/main/L0_MergeRequest_PR pipeline #43476 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54513 [ run ] triggered by Bot. Commit: 0a37901 Link to invocation

[tensorrt-cicd]

PR_Github #54513 [ run ] completed with state SUCCESS. Commit: 0a37901
/LLM/main/L0_MergeRequest_PR pipeline #43571 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54716 [ run ] triggered by Bot. Commit: 9115358 Link to invocation

[tensorrt-cicd]

PR_Github #54716 [ run ] completed with state FAILURE. Commit: 9115358
/LLM/main/L0_MergeRequest_PR pipeline #43742 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54911 [ run ] triggered by Bot. Commit: 475bbe4 Link to invocation

[tensorrt-cicd]

PR_Github #54911 [ run ] completed with state SUCCESS. Commit: 475bbe4
/LLM/main/L0_MergeRequest_PR pipeline #43914 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54962 [ run ] triggered by Bot. Commit: c80e0b1 Link to invocation

[tensorrt-cicd]

PR_Github #54962 [ run ] completed with state SUCCESS. Commit: c80e0b1
/LLM/main/L0_MergeRequest_PR pipeline #43962 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

[jieli-matrix]

/bot skip --comment "Only waive tests"

[tensorrt-cicd]

PR_Github #54978 [ skip ] triggered by Bot. Commit: de910d4 Link to invocation

[tensorrt-cicd]

PR_Github #54978 [ skip ] completed with state SUCCESS. Commit: de910d4
Skipping testing for commit de910d4

Link to invocation