Skip to content

[None][test] Waive 7 failed cases for main in QA CI - #15036

Closed
tensorrt-cicd wants to merge 1 commit into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260606-063022
Closed

[None][test] Waive 7 failed cases for main in QA CI#15036
tensorrt-cicd wants to merge 1 commit into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260606-063022

Conversation

@tensorrt-cicd

@tensorrt-cicd tensorrt-cicd commented Jun 6, 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): 6239637, 6273850, 6274932, 6274934

Waive entries added

accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16_mtp[mtp_on] SKIP (https://nvbugs/6239637)
accuracy/test_llm_api_pytorch.py::TestStep3_7::test_fp8_block_scales[tp_size=4-ep_size=4-mtp_nextn=3] SKIP (https://nvbugs/6274932)
accuracy/test_llm_api_pytorch.py::TestStep3_7::test_fp8_block_scales[tp_size=4-ep_size=4-mtp_nextn=0] SKIP (https://nvbugs/6274932)
disaggregated/test_workers.py::test_workers_conditional_disaggregation_deepseek_v3_lite_bf16[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/6274934)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16_mtp[mtp_off] SKIP (https://nvbugs/6273850)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16[tp1-CUTLASS] SKIP (https://nvbugs/6273850)
accuracy/test_llm_api_pytorch_multimodal.py::TestStep3_7::test_fp8_block_scales SKIP (https://nvbugs/6274932)

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

Summary by CodeRabbit

  • Tests
    • Updated test skip configurations to mark additional test cases as inactive, including tests for specific model variants and optimization features.

Bug(s): 6239637, 6273850, 6274932, 6274934
Requested by: qa@nvidia.com

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
@crazydemo crazydemo changed the title [None][test] Waive 7 failed cases for main in post-merge [None][test] Waive 7 failed cases for main in QA CI Jun 6, 2026
@crazydemo
crazydemo enabled auto-merge (squash) June 6, 2026 06:31
@crazydemo

Copy link
Copy Markdown
Collaborator

/bot run --stage-list ""

@coderabbitai

coderabbitai Bot commented Jun 6, 2026

Copy link
Copy Markdown
Contributor

Too much diff to scan? Review this PR in Change Stack to start with the highest-impact changes.

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: 0092f3cf-e4ae-42ea-a43a-cd520617ee59

📥 Commits

Reviewing files that changed from the base of the PR and between e47f26e and 8cfdac2.

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

📝 Walkthrough

Walkthrough

Updated test skip/waive entries in the integration test configuration file to add seven new SKIP cases for Qwen3 bf16 variants, Step3-7 fp8 block-scale accuracy tests (including multimodal), and DeepSeek-V3-Lite-bf16 disaggregated worker tests.

Changes

Test Waiver Configuration

Layer / File(s) Summary
Add Qwen3 and DeepSeek-V3-Lite test waivers
tests/integration/test_lists/waives.txt
Added SKIP entries for accuracy/test_llm_api_pytorch.py Qwen3 5B and 35B bf16 variants, multiple Step3-7 fp8 block-scale test cases for both standard and multimodal accuracy tests, and a disaggregated worker test for DeepSeek-V3-Lite-bf16.

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#14839: Both PRs modify the same file tests/integration/test_lists/waives.txt by adding new SKIP waiver entries for accuracy/test_llm_api_pytorch.py test cases.
  • NVIDIA/TensorRT-LLM#14854: Both PRs update tests/integration/test_lists/waives.txt by adding/modifying SKIP entries for overlapping DeepSeek-V3-Lite-bf16 and fp8_block_scales parameterizations.
  • NVIDIA/TensorRT-LLM#14792: Both PRs modify the same tests/integration/test_lists/waives.txt by adding additional SKIP entries for overlapping test areas like accuracy/test_llm_api_pytorch.py and disaggregated tests.

Suggested reviewers

  • crazydemo
  • jieli-matrix
  • StanleySun639
  • LarryXFly
  • xinhe-nv
🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name Status Explanation Resolution
Description check ❓ Inconclusive The description is auto-generated and lacks standard sections from the template (Description, Test Coverage, PR Checklist), though it clearly documents the waive entries and references bug IDs. Add standard PR description sections including a summary of why these tests are being waived, and confirm test coverage implications for this waive PR.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title accurately describes the main change: waiving 7 failed test cases for the main branch in CI, which matches the file modification and objectives.
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.

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52486 [ run ] triggered by Bot. Commit: 8cfdac2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #52486 [ run ] completed with state SUCCESS. Commit: 8cfdac2
/LLM/main/L0_MergeRequest_PR pipeline #41778 (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

@crazydemo

Copy link
Copy Markdown
Collaborator

close as moved to #15077

@crazydemo crazydemo closed this Jun 8, 2026
auto-merge was automatically disabled June 8, 2026 06:46

Pull request was closed

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.

2 participants