Skip to content

[None][test] Waive 9 failed cases for main in post-merge - #15391

Merged
jieli-matrix merged 7 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260616-025534
Jun 19, 2026
Merged

[None][test] Waive 9 failed cases for main in post-merge#15391
jieli-matrix merged 7 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260616-025534

Conversation

@tensorrt-cicd

@tensorrt-cicd tensorrt-cicd commented Jun 16, 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): 6316980, 6316981, 6316983, 6316984, 6316985, 6329165

Waive entries added

full:GB300/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[True-False-False-False] SKIP (https://nvbugs/6316984)
full:GB300/accuracy/test_llm_api_pytorch_multimodal.py::TestQwen2_5_VL_7B::test_auto_dtype SKIP (https://nvbugs/6316983)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[nvfp4-1-attn_dp_off-trtllm] SKIP (https://nvbugs/6329165)
full:GB300/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8_moe_dflash SKIP (https://nvbugs/6316985)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[fp8_ws4_80gb-trtllm] SKIP (https://nvbugs/6316981)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[nvfp4_ws4_80gb-trtllm] SKIP (https://nvbugs/6316981)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[bf16_ws4_180gb-trtllm] SKIP (https://nvbugs/6316981)
full:GB300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-trtllm-fp8] SKIP (https://nvbugs/6316980)
full:GB300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache_no_reuse-tp4-trtllm-fp8] SKIP (https://nvbugs/6316980)

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

Summary by CodeRabbit

  • Tests
    • Updated test waiver configuration with skip entries for GB300 target test cases and associated parameter combinations, optimizing test suite organization and execution.

@jieli-matrix
jieli-matrix enabled auto-merge (squash) June 16, 2026 02:56
@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot run --stage-list ""

@coderabbitai

coderabbitai Bot commented Jun 16, 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: 7b7856d6-c2ab-4717-a554-399db36fb485

📥 Commits

Reviewing files that changed from the base of the PR and between f49d09f and 7af7e85.

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

📝 Walkthrough

Walkthrough

Nine new SKIP waiver entries are added to tests/integration/test_lists/waives.txt for GB300 targets, inserted after the DGX_B200 Cosmos3 transformer waivers and before the GH200 section. Each entry references an NVBUG link and covers accuracy, autodeploy, pytorch, and multimodal test variants.

Changes

GB300 Test Waivers

Layer / File(s) Summary
GB300 SKIP waiver entries
tests/integration/test_lists/waives.txt
Inserts 9 SKIP waiver lines (lines 184–192) for GB300 targets covering accuracy, autodeploy, pytorch, and multimodal test parameter combinations, each annotated with an NVBUG reference.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#15373: Modifies the same waives.txt file by inserting SKIP entries for GB300-related test cases, directly overlapping in scope and target.
  • NVIDIA/TensorRT-LLM#15326: Adds SKIP waiver entries to the same waives.txt file for specific failing test parameter combinations.
  • NVIDIA/TensorRT-LLM#15358: Adds new SKIP/waiver entries to the same waives.txt file.

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 deviates significantly from the required template, lacking structured sections for Description, Test Coverage, and PR Checklist that are mandatory. Restructure the description to follow the template: add a Description section explaining the waive entries, a Test Coverage section, and complete the PR Checklist with required checkboxes.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The PR title accurately reflects the main change: adding 9 waived test cases for GB300 targets in the post-merge state on the main branch.
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 #54437 [ run ] triggered by Bot. Commit: 7af7e85 Link to invocation

@jieli-matrix
jieli-matrix force-pushed the trtllm-ci-report/waive-20260616-025534 branch from 7af7e85 to d183f1b Compare June 16, 2026 06:30
@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot run --stage-list ""

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54504 [ run ] triggered by Bot. Commit: d183f1b Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54437 [ run ] completed with state ABORTED. Commit: 7af7e85

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54504 [ run ] completed with state SUCCESS. Commit: d183f1b
/LLM/main/L0_MergeRequest_PR pipeline #43564 (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

Bug(s): 6316980, 6316981, 6316983, 6316984, 6316985, 6329165
Requested by: qa@nvidia.com

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot run --stage-list ""

@jieli-matrix
jieli-matrix force-pushed the trtllm-ci-report/waive-20260616-025534 branch from d183f1b to 65b077c Compare June 17, 2026 02:23
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54710 [ run ] triggered by Bot. Commit: 65b077c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54710 [ run ] completed with state FAILURE. Commit: 65b077c
/LLM/main/L0_MergeRequest_PR pipeline #43738 (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

@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot run --stage-list ""

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54921 [ run ] triggered by Bot. Commit: a5f3328 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54921 [ run ] completed with state SUCCESS. Commit: a5f3328
/LLM/main/L0_MergeRequest_PR pipeline #43923 (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

@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot run --stage-list ""

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54966 [ run ] triggered by Bot. Commit: bd08dd8 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54966 [ run ] completed with state SUCCESS. Commit: bd08dd8
/LLM/main/L0_MergeRequest_PR pipeline #43966 (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

Link to invocation

@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot skip --comment "Only waive tests"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54970 [ skip ] triggered by Bot. Commit: a5ae8fb Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #54970 [ skip ] completed with state SUCCESS. Commit: a5ae8fb
Skipping testing for commit a5ae8fb

Link to invocation

@jieli-matrix
jieli-matrix merged commit 3baa571 into NVIDIA:main Jun 19, 2026
7 checks passed
xinhe-nv pushed a commit to tensorrt-cicd/TensorRT-LLM that referenced this pull request Jun 23, 2026
Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
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>
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