Skip to content

[None][test] Waive 3 failed cases for main in QA CI - #19314

Merged
xinhe-nv merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260917-012553
Sep 17, 2026
Merged

xinhe-nv merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260917-012553

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Sep 17, 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): 6649739, 6758594

Waive entries added

full:GB300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-tp4-trtllm-auto] SKIP (https://nvbugs/6649739)
full:GB300/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_multi_lora_varying_ranks[cudagraph] SKIP (https://nvbugs/6758594)
full:GB300/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_multi_lora_varying_ranks[eager] SKIP (https://nvbugs/6758594)

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

Dev Engineer Review

The change updates tests/integration/test_lists/waives.txt with three GB300 SKIP waivers. The waivers cover TestGPTOSS::test_w4_4gpus for bug 6649739 and the cudagraph and eager variants of test_qwen_moe_routed_expert_multi_lora_varying_ranks for bug 6758594.

The waivers reduce test coverage for affected configurations until the tracked bugs are resolved. Review finding counts are unavailable.

QA Engineer Review

The change modifies one test-list file only. It adds three GB300 waiver entries for one GPT-OSS W4 4-GPU case and two Qwen MoE LoRA rank-variation cases. No test implementations or test functions changed. The entries use existing full:GB300 selectors and reference the associated NVIDIA bugs. Coverage is needs follow-up because the affected cases will be skipped.

Per-File QA Perspective

  • tests/integration/test_lists/waives.txt: Adds three GB300 CI skip waivers for the GPT-OSS W4 4-GPU test and the Qwen MoE LoRA cudagraph and eager variants. The entries are placed in the GB300 section and should be removed when bugs 6649739 and 6758594 are resolved.

Bug(s): 6649739, 6758594
Requested by: qa@nvidia.com

Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
@xinhe-nv
xinhe-nv enabled auto-merge (squash) September 17, 2026 01:26
@xinhe-nv

Copy link
Copy Markdown
Collaborator

/bot skip --comment "waive only"

@github-actions

Copy link
Copy Markdown

Automatically added "ci: full pre-merge approved" because this PR has satisfied the required GitHub review approvals. Unresolved review conversations and other required checks remain independent merge requirements.

@coderabbitai

coderabbitai Bot commented Sep 17, 2026

Copy link
Copy Markdown
Contributor

Review Change StackReview 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: c72326d5-24d1-4eef-9dbc-f1dcc0d50250

📥 Commits

Reviewing files that changed from the base of the PR and between 3f610d6 and 858c5ae.

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

Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review.


Walkthrough

The waiver list adds eight GB300 integration test cases. The cases cover GPT-OSS, Qwen3.5, Exaone, DeepSeek, and Qwen MoE scenarios. Each entry references an NVIDIA bug.

Changes

GB300 Test Waivers

Layer / File(s) Summary
Add GB300 waiver entries
tests/integration/test_lists/waives.txt
Added eight GB300 skip entries for GPT-OSS W4 TRT-LLM, Qwen3.5 BF16, Exaone auto-dtype, DeepSeek disaggregated, and Qwen routed-expert multi-LoRA cases.

Priority: ⬇️ Low

Estimated code review effort: 1 (Trivial) | ~3 minutes

Change: Other

Possibly related PRs

Suggested reviewers: brnguyen2

Merge Risk: ⚪ Minimal · up to 858c5

The GB300 waiver entries target the intended integration tests without introducing a concrete merge risk.

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies a test-related waiver of three failed QA CI cases on the main branch. It is concise and matches the stated objectives.
Description check ✅ Passed The description explains the automated waiver purpose, target branch, associated bugs, and all three exact SKIP entries. It does not use the template headings or include the checklist, but the core re…
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.
✨ 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 #73947 [ skip ] triggered by Bot. Commit: 858c5ae Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #73947 [ skip ] completed with state SUCCESS. Commit: 858c5ae
Skipping testing for commit 858c5ae

Link to invocation

@xinhe-nv
xinhe-nv merged commit 176ef4a into NVIDIA:main Sep 17, 2026
18 checks passed
@xinhe-nv
xinhe-nv deleted the trtllm-ci-report/waive-20260917-012553 branch September 17, 2026 02:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants