Skip to content

[None][test] Waive 6 failed cases for main in QA CI - #15570

Merged
xinhe-nv merged 4 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260624-025552
Jun 24, 2026
Merged

[None][test] Waive 6 failed cases for main in QA CI#15570
xinhe-nv merged 4 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260624-025552

Conversation

@tensorrt-cicd

@tensorrt-cicd tensorrt-cicd commented Jun 24, 2026

Copy link
Copy Markdown
Collaborator

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/2270/
Bug(s): 6274932, 6276842, 6344107

Waive entries added

full:H20/disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6344107)
full:H20/accuracy/test_llm_api_pytorch_encode.py::TestDecoderEncode::test_decoder_encode_cuda_graph_matches_eager_logits[tinyllama-1.1b] SKIP (https://nvbugs/6276842)
full:H20/accuracy/test_llm_api_pytorch_multimodal.py::TestStep3_7::test_fp8_block_scales[mtp_nextn=0] SKIP (https://nvbugs/6274932)
full:H20/accuracy/test_llm_api_pytorch_multimodal.py::TestStep3_7::test_fp8_block_scales[mtp_nextn=3] SKIP (https://nvbugs/6274932)
full:H20/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)
full:H20/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)

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

Summary by CodeRabbit

  • Tests
    • Added waivers for multiple test cases in the full:H20 environment, including FP8 block scale tests, CUDA-graph/eager matching tests, and disaggregated generation tests.

@xinhe-nv
xinhe-nv marked this pull request as ready for review June 24, 2026 02:57
@coderabbitai

coderabbitai Bot commented Jun 24, 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: 687847d3-4aa8-4ce8-808a-c696bee6ee94

📥 Commits

Reviewing files that changed from the base of the PR and between 77752ea and 6f1e6d2.

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

📝 Walkthrough

Walkthrough

Six new SKIP/waive entries are added to tests/integration/test_lists/waives.txt for the full:H20 environment. These cover TestStep3_7 FP8 block scale test cases in the PyTorch API and multimodal test modules, a CUDA-graph/eager match test in the encode module, and a disaggregated overlap generation test, each referencing specific nvbugs IDs.

Changes

H20 Integration Test Waives

Layer / File(s) Summary
H20 SKIP entries for FP8, CUDA-graph, and disaggregated tests
tests/integration/test_lists/waives.txt
Inserts six full:H20 SKIP lines for TestStep3_7 FP8 block scale variants (test_llm_api_pytorch.py, test_llm_api_pytorch_multimodal.py), a CUDA-graph/eager decode match case (test_llm_api_pytorch_encode.py), and a disaggregated overlap generation case (test_disaggregated.py), each with an associated nvbugs reference.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#15392: Adds/removes waivers for the same TestStep3_7 FP8 block-scale cases in test_llm_api_pytorch.py and test_llm_api_pytorch_multimodal.py, differing by environment and extra entries.
  • NVIDIA/TensorRT-LLM#15504: Targets the same family of Step3_7 FP8 block-scale (including multimodal) and disaggregated overlap-generation test cases with nvbug references in the same waives file.
  • NVIDIA/TensorRT-LLM#15505: Adds skip/waive entries for overlapping test files (test_llm_api_pytorch(_multimodal).py, test_disaggregated.py) targeting a different environment (full:B200).

Suggested reviewers

  • crazydemo
  • jieli-matrix
  • LarryXFly
  • StanleySun639
  • xinhe-nv
🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title '[None][test] Waive 6 failed cases for main in QA CI' follows the specified format and clearly describes the main change: adding waive entries for 6 failed test cases in the QA CI.
Description check ✅ Passed The description provides clear context about the auto-generated waiver PR, includes references to the Jenkins build and bug IDs, and lists all 6 waive entries that were added. However, it lacks the structured sections (Description and Test Coverage) specified in the template.
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.

@xinhe-nv
xinhe-nv force-pushed the trtllm-ci-report/waive-20260624-025552 branch from 6f1e6d2 to 6f04db4 Compare June 24, 2026 03:01
@xinhe-nv
xinhe-nv requested review from a team as code owners June 24, 2026 03:01
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Bug(s): 6274932, 6276842, 6344107
Requested by: qa@nvidia.com
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_FUNCTION_TEST/2270/

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
@xinhe-nv
xinhe-nv force-pushed the trtllm-ci-report/waive-20260624-025552 branch from 6f04db4 to 40f3802 Compare June 24, 2026 03:02
@xinhe-nv
xinhe-nv enabled auto-merge (squash) June 24, 2026 03:02
@xinhe-nv

Copy link
Copy Markdown
Collaborator

/bot skip --comment "Only waive test"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55409 [ skip ] triggered by Bot. Commit: 17bc379 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #126 [ skip ] triggered by Bot. Commit: 17bc379 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #126 [ skip ] completed with state SUCCESS. Commit: 17bc379
Skipping testing for commit 17bc379

Link to invocation

@xinhe-nv
xinhe-nv merged commit fb43138 into NVIDIA:main Jun 24, 2026
7 checks passed
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55409 [ skip ] completed with state SUCCESS. Commit: 17bc379
Skipping testing for commit 17bc379

Link to invocation

@xinhe-nv
xinhe-nv deleted the trtllm-ci-report/waive-20260624-025552 branch June 24, 2026 04:46
BrianLi23 pushed a commit to BrianLi23/TensorRT-LLM that referenced this pull request Jul 9, 2026
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@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.

2 participants