Skip to content

[None][test] Waive 8 failed cases for main in QA CI#16061

Open
trtllm-agent wants to merge 2 commits into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260707-093458
Open

[None][test] Waive 8 failed cases for main in QA CI#16061
trtllm-agent wants to merge 2 commits into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260707-093458

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Jul 7, 2026

Copy link
Copy Markdown
Collaborator

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 6414760, 6422318, 6422334, 6422343, 6423926

Waive entries added

full:H100/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=True-v2_kv_cache=True] SKIP (https://nvbugs/6422343)
full:H100/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=True-v2_kv_cache=False] SKIP (https://nvbugs/6422343)
full:H100/test_e2e.py::test_multi_nodes_eval[Qwen3/Qwen3-235B-A22B-tp16-mmlu] SKIP (https://nvbugs/6423926)
full:H100/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[llguidance-eagle3_one_model=False] SKIP (https://nvbugs/6422334)
full:H100/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[xgrammar-eagle3_one_model=False] SKIP (https://nvbugs/6422334)
full:H100/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6422318)
full:H100/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6422318)
full:H100/test_e2e.py::test_qwen_e2e_cpprunner_large_new_tokens[DeepSeek-R1-Distill-Qwen-1.5B-DeepSeek-R1-Distill-Qwen-1.5B] SKIP (https://nvbugs/6414760)

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

Summary by CodeRabbit

  • Tests
    • Expanded test waivers for several H100 integration and end-to-end scenarios.
    • Added skips for additional guided decoding, multimodal, and large-token test cases.
    • Preserved existing H100 waivers while reorganizing the list.

Bug(s): 6414760, 6422318, 6422334, 6422343, 6423926
Requested by: qa@nvidia.com

Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
@jieli-matrix jieli-matrix enabled auto-merge (squash) July 7, 2026 09:35
@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot skip --comment "Only waive tests"

@coderabbitai

coderabbitai Bot commented Jul 7, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

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: 023e81df-e0a4-4a92-9449-377891ec35bf

📥 Commits

Reviewing files that changed from the base of the PR and between dc49938 and 22318ad.

📒 Files selected for processing (1)
  • tests/integration/test_lists/waives.txt

📝 Walkthrough

Walkthrough

This PR adds new SKIP waiver entries to the H100 test waiver list, covering guided decoding with Eagle3, DeepSeekV3Lite bfloat16 mtp_nextn=2 variants, Exaone4_5_33B multimodal auto-dtype cases, and additional e2e test skips, while retaining existing waivers.

Changes

H100 Waiver List Update

Layer / File(s) Summary
Add new H100 SKIP entries
tests/integration/test_lists/waives.txt
New SKIP entries added for guided decoding (Eagle3, llguidance/xgrammar), DeepSeekV3Lite bfloat16 mtp_nextn=2 variants, Exaone4_5_33B auto-dtype variants, multi-nodes eval, and Qwen cpprunner cases; existing waivers retained and repositioned.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#16030: Both PRs add H20/H100 guided-decoding and DeepSeekV3Lite/Exaone4_5_33B multimodal auto-dtype waiver entries to the same file.
  • NVIDIA/TensorRT-LLM#16034: Both PRs add overlapping SKIP entries for TestDeepSeekV3Lite (bfloat16/v2_kv_cache), TestExaone4_5_33B::test_auto_dtype variants, and Qwen cpprunner e2e cases.
  • NVIDIA/TensorRT-LLM#15733: Both PRs add SKIP entries for DeepSeekV3Lite test_auto_dtype/test_guided_decoding bfloat16 cases in the same waiver list.

Suggested reviewers: jieli-matrix

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description includes the waived entries and bugs, but it lacks the required Description, Test Coverage, and PR Checklist sections. Add the template sections, briefly explain why each waiver is needed, include test coverage, and complete the PR checklist.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly states this PR waives eight failed QA CI cases on main.
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.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57988 [ skip ] triggered by Bot. Commit: 22318ad Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57988 [ skip ] completed with state SUCCESS. Commit: 22318ad
Skipping testing for commit 22318ad

Link to invocation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants