[None][infra] Waive 3 failed cases for main in post-merge - #13789
Conversation
📝 WalkthroughWalkthroughThree test cases were added to the waiver list to skip due to known issues tracked in bug reports: a disaggregated TinyLlama overlap test, a Qwen3 VL multimodal auto-dtype test, and a Qwen3.5 4B bf16 accuracy test. ChangesTest Waivers
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Comment |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@tests/integration/test_lists/waives.txt`:
- Around line 441-443: The three waiver entries appended at the end of
tests/integration/test_lists/waives.txt are out of alphabetical order and must
be sorted: move the "ctx_pp1-TinyLlama-1.1B-Chat-v1.0" entry so it appears
before the existing ctx_pp4 entry (i.e., near the earlier ctx_pp* block), and
insert the two accuracy entries
("accuracy/test_llm_api_pytorch_multimodal.py::TestQwen3VL::test_auto_dtype[forced_chunked_prefill]"
and "accuracy/test_llm_api_pytorch.py::TestQwen3_5_4B::test_bf16") into their
respective accuracy/* section in alphabetical order; easiest fix is to run the
pre-commit hook file-contents-sorter (pre-commit run file-contents-sorter
--files tests/integration/test_lists/waives.txt) and commit the sorted file.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 30ed369f-08f1-4230-9f37-2a412c831566
📒 Files selected for processing (1)
tests/integration/test_lists/waives.txt
|
/bot run --stage-list "" |
891ba4b to
f9d5541
Compare
|
/bot run --stage-list "" |
|
PR_Github #46899 [ run ] triggered by Bot. Commit: |
|
PR_Github #46899 [ run ] completed with state |
|
/bot reuse-pipeline |
|
PR_Github #46920 [ reuse-pipeline ] triggered by Bot. Commit: |
|
PR_Github #46920 [ reuse-pipeline ] completed with state |
Bug(s): 6141803, 6141806, 6143787 Requested by: qa@nvidia.com Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Signed-off-by: Jie Li <lijie@nvidia.com>
4bde7d3 to
f31f730
Compare
|
/bot reuse-pipeline |
|
PR_Github #46933 [ reuse-pipeline ] triggered by Bot. Commit: |
|
PR_Github #46933 [ reuse-pipeline ] completed with state |
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
Auto-generated Waive PR
Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch:
mainBug(s): 6141803, 6141806, 6143787
Waive entries added
This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.
Summary by CodeRabbit