Skip to content

[None][test] Waive 6 failed cases for main in QA CI - #17180

Merged
xinhe-nv merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260803-055857
Aug 3, 2026
Merged

[None][test] Waive 6 failed cases for main in QA CI#17180
xinhe-nv merged 1 commit into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260803-055857

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Aug 3, 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): 6474894, 6528742, 6539942, 6546609, 6546909

Waive entries added

full:GB300/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-dp4-trtllm-fp8] SKIP (https://nvbugs/6474894)
full:GB300/accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[bf16-4-attn_dp_off-trtllm] SKIP (https://nvbugs/6539942)
full:GB300/accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_fp8_4gpus[attention_dp_off-python_mamba_cache] SKIP (https://nvbugs/6528742)
full:GB300/accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_fp8_4gpus[attention_dp_on-python_mamba_cache] SKIP (https://nvbugs/6528742)
full:GB300/accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8[fp8kv=False-attn_backend=TRTLLM-torch_compile=True] SKIP (https://nvbugs/6546909)
full:GB300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV4FlashBase::test_fp8_4gpus_static_eplb[moe_backend=WIDEEP] SKIP (https://nvbugs/6546609)

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

Dev Engineer Review

  • Added six GB300 QA waivers in tests/integration/test_lists/waives.txt.
  • The entries cover the stated Nemotron Nano, DeepSeek V4 Flash, GPTOSS, Llama, and Nemotron V3 Super configurations.
  • The entries reference bugs 6474894, 6528742, 6539942, 6546609, and 6546909.
  • No public APIs or code paths changed.
  • Waiver scope remains limited to GB300 accuracy tests.

QA Engineer Review

  • Modified tests/integration/test_lists/waives.txt.
  • Added six waiver entries.
  • Removed no entries.
  • Five entries target test_llm_api_pytorch.py.
  • One entry targets test_llm_api_autodeploy.py.
  • CBTS coverage data is unavailable.
  • Verdict: needs follow-up.

Bug(s): 6474894, 6528742, 6539942, 6546609, 6546909
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) August 3, 2026 05:59
@coderabbitai

coderabbitai Bot commented Aug 3, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

Walkthrough

The GB300 waiver list now includes 17 skipped integration test configurations for Nemotron, DeepSeek, GPTOSS, Gemma, Llama, MiniMax, and related models. Each entry includes an NV bug reference.

Changes

GB300 test waivers

Layer / File(s) Summary
Add GB300 skip entries
tests/integration/test_lists/waives.txt
Added 17 SKIP entries for model and configuration-specific GB300 tests. Each entry includes an NV bug reference.

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

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 and the six failed QA CI cases on the main branch.
Description check ✅ Passed The description explains the automated waiver purpose, target branch, bug references, and all six skipped test entries.
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.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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`:
- Line 232: Add the repository-standard NVIDIA copyright header to
tests/integration/test_lists/waives.txt, updating the copyright year to the
current required year while preserving the existing waiver entry unchanged.
🪄 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: cc71c088-8221-4849-964e-9bb0da92d734

📥 Commits

Reviewing files that changed from the base of the PR and between c0836f0 and fc727dd.

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

Comment thread tests/integration/test_lists/waives.txt
@xinhe-nv

xinhe-nv commented Aug 3, 2026

Copy link
Copy Markdown
Collaborator

/bot skip --comment "waive failed tests"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #63368 [ skip ] triggered by Bot. Commit: fc727dd Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #63368 [ skip ] completed with state SUCCESS. Commit: fc727dd
Skipping testing for commit fc727dd

Link to invocation

@xinhe-nv
xinhe-nv merged commit 74f3ccf into NVIDIA:main Aug 3, 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