Skip to content

[None][test] Waive 7 failed cases for main in QA CI - #19408

Merged
xinhe-nv merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260918-065222
Sep 18, 2026
Merged

xinhe-nv merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260918-065222

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Sep 18, 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): 6672360, 6758594, 6776338, 6799208, 6801098, 6801102, 6801419

Waive entries added

full:GB200/disaggregated/test_disaggregated.py::test_disaggregated_overlap[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6799208)
full:GB200/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention[target_sparsity_0.9-fp8kv=True] SKIP (https://nvbugs/6801419)
full:GB200/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v2_kv_cache-True-True-trtllm-fp8] SKIP (https://nvbugs/6672360)
full:GB200/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_multi_lora_varying_ranks[eager] SKIP (https://nvbugs/6758594)
full:GB200/accuracy/test_llm_api_pytorch_multimodal.py::TestQwen3_5_35B_A3B_VL::test_fp8_prequantized SKIP (https://nvbugs/6776338)
full:GB200/accuracy/test_llm_api_pytorch_multimodal.py::TestQwen3VL::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6801098)
full:GB200/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_mxfp8_piecewise_cuda_graph[use_msa=True] SKIP (https://nvbugs/6801102)

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

Dev Engineer Review

The change adds seven GB200 entries to tests/integration/test_lists/waives.txt. It does not change source code or runtime behavior. The waivers reduce CI coverage for the affected test cases until bugs 6672360, 6758594, 6776338, 6799208, 6801098, 6801102, and 6801419 are resolved.

QA Engineer Review

The change modifies only the waiver list and adds seven GB200 waivers covering disaggregated, accuracy, LLM API, multimodal, and MoE LoRA cases. No test implementations or test functions changed. Coverage verdict: needs follow-up, because the change suppresses failed CI cases and no fix or waiver expiry is included.

Per-File QA Perspective

  • tests/integration/test_lists/waives.txt: Adds seven GB200 CI waivers linked to the seven reported bugs. QA should track the failures and remove the waivers after the fixes are verified; no related test-db/ or qa/ list changes are shown.

Bug(s): 6672360, 6758594, 6776338, 6799208, 6801098, 6801102, 6801419
Requested by: qa@nvidia.com

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

Copy link
Copy Markdown
Collaborator

/bot skip --comment "waive tests 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 18, 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: 575467a0-f18f-45e6-8a8b-2f7c51b7c0c3

📥 Commits

Reviewing files that changed from the base of the PR and between bb604eb and 1b748aa.

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

Included review availability: Your plan provides up to 12 included reviews per hour; 9 remain after this review.


Walkthrough

The integration waiver list adds seven GB200-specific entries for GPTOSS, MiniMax, Qwen, TinyLlama, and multimodal test cases. Each entry includes a corresponding NVIDIA bug reference.

Changes

GB200 integration waivers

Layer / File(s) Summary
Add GB200 waiver entries
tests/integration/test_lists/waives.txt
Adds seven GB200 waivers covering quantization, CUDA graphs, sparse attention, multimodal dtype handling, disaggregated overlap, and multi-LoRA tests.

Priority: ⬇️ Low

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

Change: Other

Possibly related PRs

Suggested reviewers: qijune

Merge Risk: ⚪ Minimal · up to 1b748

The seven GB200 waiver entries are scoped and formatted as expected, so the change is ready to merge.

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies that seven failed QA CI cases will be waived on the main branch. It is concise and directly matches the pull request changes.
Description check ✅ Passed The description clearly identifies the automated source, target branch, seven associated bugs, and all seven waiver entries. It does not use the template's Description, Test Coverage, or PR Checklist …
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 a new PR

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

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #74353 [ skip ] triggered by Bot. Commit: 1b748aa Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #74353 [ skip ] completed with state SUCCESS. Commit: 1b748aa
Skipping testing for commit 1b748aa

Link to invocation

@xinhe-nv
xinhe-nv merged commit dcc95a8 into NVIDIA:main Sep 18, 2026
18 checks passed
@xinhe-nv
xinhe-nv deleted the trtllm-ci-report/waive-20260918-065222 branch September 18, 2026 07:19
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