Skip to content

[None][test] Waive 9 failed cases for main in QA CI - #15504

Merged
xinhe-nv merged 9 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260620-074925
Jun 23, 2026
Merged

[None][test] Waive 9 failed cases for main in QA CI#15504
xinhe-nv merged 9 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260620-074925

Conversation

@tensorrt-cicd

@tensorrt-cicd tensorrt-cicd commented Jun 20, 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_CLUSTER_TEST/1551/
Bug(s): 6274932, 6313072, 6344107, 6344108

Waive entries added

full:H100/accuracy/test_llm_api_pytorch_multimodal.py::TestStep3_7::test_fp8_block_scales[mtp_nextn=0] SKIP (https://nvbugs/6274932)
full:H100/accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=True] SKIP (https://nvbugs/6313072)
full:H100/accuracy/test_llm_api_pytorch_multimodal.py::TestStep3_7::test_fp8_block_scales[mtp_nextn=3] SKIP (https://nvbugs/6274932)
full:H100/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)
full:H100/accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False] SKIP (https://nvbugs/6313072)
full:H100/disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6344107)
full:H100/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:H100/accuracy/test_disaggregated_serving.py::TestNemotron3Super120B::test_auto_dtype[mtp_nextn=3-block_reuse=True-use_py_transceiver=False] SKIP (https://nvbugs/6344108)
full:H100/accuracy/test_disaggregated_serving.py::TestNemotron3Super120B::test_ctx_dp2_gen_tp4 SKIP (https://nvbugs/6344108)

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

Summary by CodeRabbit

  • Tests
    • Expanded H100-specific test waive entries for additional scenario configurations.

@xinhe-nv
xinhe-nv force-pushed the trtllm-ci-report/waive-20260620-074925 branch from d8f1fac to 9ed47b3 Compare June 23, 2026 05:28
@xinhe-nv
xinhe-nv marked this pull request as ready for review June 23, 2026 05:29
@xinhe-nv
xinhe-nv force-pushed the trtllm-ci-report/waive-20260620-074925 branch from 9ed47b3 to 4c5a590 Compare June 23, 2026 05:29
@xinhe-nv
xinhe-nv enabled auto-merge (squash) June 23, 2026 05:29
tensorrt-cicd and others added 4 commits June 23, 2026 05:29
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Bug(s): 6274932, 6313072, 6344107, 6344108
Requested by: qa@nvidia.com
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_FUNCTION_CLUSTER_TEST/1551/

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
@xinhe-nv
xinhe-nv force-pushed the trtllm-ci-report/waive-20260620-074925 branch from 4c5a590 to ef14535 Compare June 23, 2026 05:29
@coderabbitai

coderabbitai Bot commented Jun 23, 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: 839c5fa2-bcd0-4c98-8464-86d0c912918e

📥 Commits

Reviewing files that changed from the base of the PR and between 683a70c and 056a51a.

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

📝 Walkthrough

Walkthrough

Five new H100 SKIP waiver entries are added to tests/integration/test_lists/waives.txt, expanding the existing H100 waiver block. The additions cover DeepSeekV3Lite test_auto_dtype with mtp_nextn=2 for both overlap_scheduler values, Nemotron3Super120B test_auto_dtype and test_ctx_dp2_gen_tp4, and test_disaggregated_overlap_gen_first for ctx_pp4-TinyLlama-1.1B-Chat-v1.0.

Changes

H100 Test Waiver Additions

Layer / File(s) Summary
New H100 SKIP waiver entries
tests/integration/test_lists/waives.txt
Expands the H100 waiver block (lines 226–237) by adding five new SKIP entries: DeepSeekV3Lite test_auto_dtype for mtp_nextn=2 with both overlap_scheduler values, Nemotron3Super120B test_auto_dtype and test_ctx_dp2_gen_tp4, and test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0].

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#15320: Also adds waivers in waives.txt for DeepSeekV3Lite mtp_nextn=2 cases, directly overlapping the same waiver area.
  • NVIDIA/TensorRT-LLM#15505: Adds the same test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0] waiver entry alongside other model-specific waives.
  • NVIDIA/TensorRT-LLM#15377: Modifies the same waives.txt file with TestStep3_7::test_auto_dtype waiver entries that overlap with existing entries in this block.

Suggested reviewers

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

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description is auto-generated but lacks required sections from the template (Description, Test Coverage, PR Checklist) and does not follow the standard title format with ticket ID and type. Add missing sections including a proper Description section explaining the purpose, Test Coverage section, and ensure the PR follows the standard title format with ticket ID/type as specified in the template.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly summarizes the main change: waiving 9 failed test cases for CI, which matches the actual content of the PR perfectly.
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

Copy link
Copy Markdown
Collaborator

/bot skip --comment "only waive tests"

xinhe-nv added 3 commits June 23, 2026 13:32
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55169 [ skip ] triggered by Bot. Commit: 209d621 Link to invocation

Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55169 [ skip ] completed with state SUCCESS. Commit: 209d621
Skipping testing for commit 209d621

Link to invocation

@xinhe-nv

Copy link
Copy Markdown
Collaborator

/bot reuse-pipeline

@xinhe-nv

Copy link
Copy Markdown
Collaborator

/bot skip --comment "Only waive tests"

@xinhe-nv

Copy link
Copy Markdown
Collaborator

/bot reuse-pipeline

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55173 [ reuse-pipeline ] triggered by Bot. Commit: 4dd4423 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55174 [ reuse-pipeline ] triggered by Bot. Commit: 4dd4423 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55173 [ reuse-pipeline ] completed with state ABORTED. Commit: 4dd4423
Can't reuse PR_Github #0 with status: UNKNOWN

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55176 [ skip ] triggered by Bot. Commit: 4dd4423 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55174 [ reuse-pipeline ] completed with state ABORTED. Commit: 4dd4423
Can't reuse PR_Github #0 with status: UNKNOWN

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55176 [ skip ] completed with state SUCCESS. Commit: 4dd4423
Skipping testing for commit 4dd4423

Link to invocation

@xinhe-nv
xinhe-nv merged commit aea4086 into NVIDIA:main Jun 23, 2026
7 checks passed
@xinhe-nv
xinhe-nv deleted the trtllm-ci-report/waive-20260620-074925 branch June 23, 2026 06:15
xinhe-nv pushed a commit to tensorrt-cicd/TensorRT-LLM that referenced this pull request Jun 24, 2026
Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Co-authored-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
BrianLi23 pushed a commit to BrianLi23/TensorRT-LLM that referenced this pull request Jul 9, 2026
Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Co-authored-by: GitLab CI Bot <gitlab-ci@nvidia.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