Skip to content

[None][test] Waive 9 failed cases for main in QA CI#16058

Merged
jieli-matrix merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260707-092044
Jul 7, 2026
Merged

[None][test] Waive 9 failed cases for main in QA CI#16058
jieli-matrix merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260707-092044

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): 6316983, 6336990, 6410881, 6414760, 6422318, 6422343, 6423845, 6423866

Waive entries added

full:B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[latency] SKIP (https://nvbugs/6423866)
full:B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline_pp4_mtp1] SKIP (https://nvbugs/6423845)
full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestQwen2_5_VL_7B::test_auto_dtype SKIP (https://nvbugs/6316983)
full:B300/accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype_with_helix[nccl-cudagraph:with_padding-pp1tp2cp2] SKIP (https://nvbugs/6410881)
full:B300/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:B300/accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_nvfp4_4gpu_mtp_ar SKIP (https://nvbugs/6336990)
full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6422318)
full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6422318)
full:B300/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 skip waivers for the B300 configuration across multiple serving, accuracy, multimodal, and end-to-end test areas.
    • Added support for additional model-specific test exclusions while keeping existing waivers in place.

Bug(s): 6316983, 6336990, 6410881, 6414760, 6422318, 6422343, 6423845, 6423866
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 09:21
@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: a061c3bf-718e-4005-84f4-6194047c47ff

📥 Commits

Reviewing files that changed from the base of the PR and between 32a953b and ccec310.

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

📝 Walkthrough

Walkthrough

This PR expands the full:B300 waivers block in the test integration waiver list, adding nine new SKIP entries for DeepSeek V3 Lite/V32 accuracy tests, Nemotron V3 Super, Exaone4.5 33B multimodal, Qwen2.5 VL 7B, and an e2e cpprunner test.

Changes

Waiver list update

Layer / File(s) Summary
Add new B300 skip entries
tests/integration/test_lists/waives.txt
Adds nine new SKIP/waiver lines to the full:B300 block for DeepSeek V3 Lite/V32 (including nccl-cudagraph and nvfp4_multi_gpus variants), Nemotron V3 Super, Exaone4.5 33B multimodal auto_dtype cases, Qwen2.5 VL 7B auto_dtype, and a Qwen e2e cpprunner test.

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

Possibly related PRs

  • NVIDIA/TensorRT-LLM#15967: Both PRs expand the same full:B300 SKIP entries in waives.txt with additional test variants.
  • NVIDIA/TensorRT-LLM#16034: Both PRs add SKIP entries for the same disaggregated/accuracy/e2e test cases around DeepSeekV3Lite, Exaone4.5 33B, and Qwen e2e cpprunner.
  • NVIDIA/TensorRT-LLM#15902: Both PRs modify the same full:B300 waiver block adding SKIP entries for DeepSeek V3 Lite configurations.

Suggested reviewers: jieli-matrix

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description is useful but misses the template's Description, Test Coverage, and PR Checklist sections. Add the required sections with a short issue/solution summary, the relevant tests, and the PR checklist confirmation.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly states this PR waives nine CI failures on main, matching the main change.
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 #57986 [ skip ] triggered by Bot. Commit: ccec310 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57986 [ skip ] completed with state SUCCESS. Commit: ccec310
Skipping testing for commit ccec310

Link to invocation

@jieli-matrix jieli-matrix merged commit dc49938 into NVIDIA:main Jul 7, 2026
12 checks passed
BrianLi23 pushed a commit to BrianLi23/TensorRT-LLM that referenced this pull request Jul 9, 2026
Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
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