Skip to content

[None][test] Waive 3 failed cases for main in QA CI - #15509

Merged
xinhe-nv merged 4 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260621-070137
Jun 23, 2026
Merged

[None][test] Waive 3 failed cases for main in QA CI#15509
xinhe-nv merged 4 commits into
NVIDIA:mainfrom
tensorrt-cicd:trtllm-ci-report/waive-20260621-070137

Conversation

@tensorrt-cicd

@tensorrt-cicd tensorrt-cicd commented Jun 21, 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/2269/
Bug(s): 6313072

Waive entries added

full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6313072)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=False] SKIP (https://nvbugs/6313072)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_batch_waiting[batch_wait_timeout_iters=10-batch_wait_max_tokens_ratio=1.0-mtp_nextn=0-fp8kv=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False-v2_kv_cache=True] SKIP (https://nvbugs/6313072)

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 for RTX_PRO_6000_Blackwell_Server_Edition to skip specific test configurations for improved hardware compatibility testing.

@xinhe-nv
xinhe-nv marked this pull request as ready for review June 23, 2026 02:57
@xinhe-nv
xinhe-nv enabled auto-merge (squash) June 23, 2026 02:58
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
Bug(s): 6313072
Requested by: qa@nvidia.com
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_FUNCTION_TEST/2269/

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-20260621-070137 branch from 0b48939 to cacc39a Compare June 23, 2026 03:00
@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: caa53fa2-f516-483e-88c3-c817976c827c

📥 Commits

Reviewing files that changed from the base of the PR and between e2c7c4f and 0b48939.

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

📝 Walkthrough

Walkthrough

Three SKIP waiver entries are added to tests/integration/test_lists/waives.txt for TestDeepSeekV3Lite on RTX_PRO_6000_Blackwell_Server_Edition, covering two test_bfloat16 parameterizations (varying torch_compile, v2_kv_cache, and overlap_scheduler) and one test_nvfp4_batch_waiting parameterization.

Changes

TestDeepSeekV3Lite RTX PRO 6000 Blackwell Waivers

Layer / File(s) Summary
Waiver entries for TestDeepSeekV3Lite
tests/integration/test_lists/waives.txt
Adds three SKIP lines for RTX_PRO_6000_Blackwell_Server_Edition: test_bfloat16[torch_compile=True, v2_kv_cache=True], test_bfloat16[overlap_scheduler=True, torch_compile=False, v2_kv_cache=False], and test_nvfp4_batch_waiting with specified batch-waiting and scheduler parameters.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#15320: Modifies the same waives.txt file with TestDeepSeekV3Lite waiver entries for different test parameterizations.
  • NVIDIA/TensorRT-LLM#15341: Updates waives.txt with SKIP entries for other failing test cases in the same waiver infrastructure.
  • NVIDIA/TensorRT-LLM#15342: Adds SKIP entries to the same waives.txt file for additional failing test cases.

Suggested reviewers

  • crazydemo
  • LarryXFly
  • StanleySun639
  • xinhe-nv
  • jieli-matrix
🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title '[None][test] Waive 3 failed cases for main in QA CI' clearly summarizes the main change: waiving 3 failed test cases in QA CI for the main branch.
Description check ✅ Passed The PR description adequately documents the auto-generated waive PR with relevant context: creator, target branch, Jenkins build link, bug tracking, and specific waive entries added.
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"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55136 [ skip ] triggered by Bot. Commit: 2559eb2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #120 [ skip ] triggered by Bot. Commit: 2559eb2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #55136 [ skip ] completed with state SUCCESS. Commit: 2559eb2
Skipping testing for commit 2559eb2

Link to invocation

@xinhe-nv
xinhe-nv merged commit 3448424 into NVIDIA:main Jun 23, 2026
7 checks passed
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator Author

PR_Github #120 [ skip ] completed with state SUCCESS. Commit: 2559eb2
Skipping testing for commit 2559eb2

Link to invocation

@xinhe-nv
xinhe-nv deleted the trtllm-ci-report/waive-20260621-070137 branch June 23, 2026 04:00
xinhe-nv added 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>
Co-authored-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.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>
Co-authored-by: xinhe-nv <200704525+xinhe-nv@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