Skip to content

[None][test] Waive 5 failed cases for main in QA CI - #18177

Merged
jieli-matrix merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260825-054701
Aug 25, 2026
Merged

[None][test] Waive 5 failed cases for main in QA CI#18177
jieli-matrix merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260825-054701

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Aug 25, 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): 6627979, 6662724

Waive entries added

full:H100/test_e2e.py::test_eagle3_output_repetition_4gpus[Qwen3/Qwen3-30B-A3B-Qwen3/Qwen3-30B-eagle3] SKIP (https://nvbugs/6627979)
full:H100/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=True-v2_kv_cache=True] SKIP (https://nvbugs/6662724)
full:H100/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=True-v2_kv_cache=False] SKIP (https://nvbugs/6662724)
full:H100/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=True-v2_kv_cache=True] SKIP (https://nvbugs/6662724)
full:H100/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=True-v2_kv_cache=False] SKIP (https://nvbugs/6662724)

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

Dev Engineer Review

  • The change adds five SKIP entries in tests/integration/test_lists/waives.txt.
  • The entries target the reported Eagle3 repetition failure and four DeepSeekV3Lite bfloat16 accuracy failures on H100 configurations.
  • The waiver scope is limited to the reported QA failures.
  • No code, API, performance, or error-handling changes are included.
  • Review should confirm that each entry uses a valid test path, the correct bug reference, and does not duplicate an existing waiver.

QA Engineer Review

  • Only tests/integration/test_lists/waives.txt was modified.
  • Five H100 waiver entries were added.
  • No test-db or qa files were modified.
  • CBTS coverage data is unavailable.
  • Verdict: needs follow-up.

Bug(s): 6627979, 6662724
Requested by: qa@nvidia.com

Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
@jieli-matrix

Copy link
Copy Markdown
Collaborator

/bot skip --comment "Only waive tests"

@coderabbitai

coderabbitai Bot commented Aug 25, 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: 7915ab58-0835-4e4c-a440-04812e40e9ea

📥 Commits

Reviewing files that changed from the base of the PR and between 36b424e and fdb17fa.

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

Included review availability: Your plan provides up to 12 included reviews per hour; 10 remain after this review.


Walkthrough

The waiver list adds four skipped H100 DeepSeekV3Lite bfloat16 test configurations. The entries cover TorchCompile and v2 KV-cache combinations with chunked prefill and overlapping CUDA-graph scheduling.

Changes

DeepSeekV3Lite H100 waivers

Layer / File(s) Summary
Add H100 waiver entries
tests/integration/test_lists/waives.txt
Adds four skipped DeepSeekV3Lite bfloat16 configurations for TorchCompile and v2 KV-cache combinations.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Merge Risk: ⚪ Minimal · up to fdb17

This PR adds five targeted QA CI waiver entries; no actionable merge-blocking risk remains, so it is merge-ready after normal checks.

Possibly related PRs

Suggested reviewers: bowenfu, qijune

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies the test waiver action, the number of failed cases, and the target branch.
Description check ✅ Passed The description explains the auto-generated waiver, identifies the related bugs, and lists all five affected H100 test cases. It provides the required technical context for this waiver PR, although it…
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
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.
Full details: Description check

Explanation

The description explains the auto-generated waiver, identifies the related bugs, and lists all five affected H100 test cases. It provides the required technical context for this waiver PR, although it does not reproduce the template headings.

Full details: Docstring Coverage

Explanation

No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0 files. (1 skipped: 1 unsupported.)

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands.

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #69022 [ skip ] triggered by Bot. Commit: fdb17fa Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #69022 [ skip ] completed with state SUCCESS. Commit: fdb17fa
Skipping testing for commit fdb17fa

Link to invocation

@jieli-matrix
jieli-matrix merged commit c850fb4 into NVIDIA:main Aug 25, 2026
13 checks passed
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.

3 participants