Skip to content

[None][test] Waive 9 failed cases for main in QA CI - #15867

Merged
xinhe-nv merged 2 commits into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260702-045133
Jul 2, 2026
Merged

[None][test] Waive 9 failed cases for main in QA CI#15867
xinhe-nv merged 2 commits into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260702-045133

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Jul 2, 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): 6388212, 6400067, 6402495, 6402500

Waive entries added

full:GB200/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/6400067)
full:GB200/disaggregated/test_ad_disagg.py::test_async_generation_no_overlap_matches_aggregate SKIP (https://nvbugs/6402495)
full:GB200/disaggregated/test_ad_disagg_trtllm_serve.py::test_openai_completion SKIP (https://nvbugs/6402495)
full:GB200/disaggregated/test_ad_disagg.py::test_async_sharded_generation_handoff SKIP (https://nvbugs/6402495)
full:GB200/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/6400067)
full:GB200/accuracy/test_llm_api_pytorch_multimodal.py::TestGemma3_27BInstruct::test_fp8_prequantized SKIP (https://nvbugs/6388212)
full:GB200/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[xgrammar-eagle3_one_model=False] SKIP (https://nvbugs/6402500)
full:GB200/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[llguidance-eagle3_one_model=False] SKIP (https://nvbugs/6402500)
full:GB200/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_eagle3[eagle3_one_model=False-overlap_scheduler=False] SKIP (https://nvbugs/6402500)

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

Summary by CodeRabbit

  • Tests
    • Updated integration test waivers to cover additional GB200 scenarios, including more accuracy, serving, and multimodal cases.
    • Adjusted several existing GB200 test exemptions to reflect current expected behavior.

Bug(s): 6388212, 6400067, 6402495, 6402500
Requested by: qa@nvidia.com

Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
@xinhe-nv
xinhe-nv enabled auto-merge (squash) July 2, 2026 04:51
@coderabbitai

coderabbitai Bot commented Jul 2, 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: 351a5d82-2238-4e1a-8a1f-30017d8b9ab4

📥 Commits

Reviewing files that changed from the base of the PR and between 9ff00c8 and ae53a1d.

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

📝 Walkthrough

Walkthrough

Updates the GB200 section of tests/integration/test_lists/waives.txt, adding waivers for Llama3.1 EAGLE3, DeepSeekV3Lite bfloat16, and Gemma3 multimodal test cases, and replacing the disaggregated serving waiver with multiple async generation/handoff and OpenAI completion waivers.

Changes

GB200 waiver list updates

Layer / File(s) Summary
GB200 waiver entries
tests/integration/test_lists/waives.txt
Adds waivers for Llama3.1 EAGLE3 overlap scheduling/guided decoding, DeepSeekV3Lite bfloat16 configurations, Gemma3 fp8 prequantized multimodal, and expands disaggregated serving waivers to multiple async generation/handoff scenarios plus an OpenAI completion test.

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

Possibly related PRs

  • NVIDIA/TensorRT-LLM#15733: Both PRs edit waives.txt for the same DeepSeekV3Lite disaggregated-serving/LLM-API test cases across different Blackwell config sections.
  • NVIDIA/TensorRT-LLM#15764: Both PRs modify waives.txt entries for DeepSeekV3Lite/GB200-related config skips.
  • NVIDIA/TensorRT-LLM#14450: Both PRs add/remove waiver entries in the same file including overlapping Gemma3 fp8 prequantized cases.

Suggested reviewers: xinhe-nv, jieli-matrix, StanleySun639

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description lists waived entries and bugs, but it omits the template's Description, Test Coverage, and PR Checklist sections. Add the required Description, Test Coverage, and PR Checklist sections and briefly explain what changed and why.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly matches the main change: waiving 9 failed 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.

@xinhe-nv

xinhe-nv commented Jul 2, 2026

Copy link
Copy Markdown
Collaborator

/bot skip --comment "only waive tests"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57127 [ skip ] triggered by Bot. Commit: caac0b7 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57127 [ skip ] completed with state SUCCESS. Commit: caac0b7
Skipping testing for commit caac0b7

Link to invocation

@xinhe-nv
xinhe-nv merged commit dc02d58 into NVIDIA:main Jul 2, 2026
7 checks passed
@xinhe-nv
xinhe-nv deleted the trtllm-ci-report/waive-20260702-045133 branch July 2, 2026 05:49
evezhier pushed a commit to evezhier/TensorRT-LLM that referenced this pull request Jul 2, 2026
Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
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