Skip to content

[https://nvbugs/6618102][chore] Unwaive multi gpu pp tests - #17989

Merged
cascade812 merged 3 commits into
NVIDIA:mainfrom
cascade812:guiju/unwaive5
Aug 21, 2026
Merged

[https://nvbugs/6618102][chore] Unwaive multi gpu pp tests#17989
cascade812 merged 3 commits into
NVIDIA:mainfrom
cascade812:guiju/unwaive5

Conversation

@cascade812

@cascade812 cascade812 commented Aug 19, 2026

Copy link
Copy Markdown
Collaborator

Dev Engineer Review

  • Updated tests/integration/test_lists/waives.txt.
  • Added skip entries for disaggregated serving, model accuracy, scheduler, MoE, visual-generation, KV-cache, coverage, and hardware-specific tests.
  • Updated the LagunaXS waiver bug reference.
  • Replaced one performance waiver.
  • Removed obsolete waivers for LagunaXS FP8, Qwen3.5 variants, visual-generation tests, hardware-specific performance tests, RocketKV tests, and performance benchmarks.
  • No code, API, performance, or error-handling changes were made.
  • The waiver file format remains consistent.

QA Engineer Review

  • Modified test-db/ files: none.
  • Modified qa/ files: none.
  • Updated entries in tests/integration/test_lists/waives.txt.
  • CBTS coverage data is unavailable.
  • Verdict: needs follow-up.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

  • PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

  • PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

  • Test cases are provided for new code paths (see test instructions)

  • If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • Update tava architecture diagram if there is a significant design change in PR.

  • The reviewers assigned automatically/manually are appropriate for the PR.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

Signed-off-by: Guiju Zhang <7135567+cascade812@users.noreply.github.com>
@coderabbitai

coderabbitai Bot commented Aug 19, 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: 2bb0d7ab-6ead-42bb-a6d0-5d59660b3478

📥 Commits

Reviewing files that changed from the base of the PR and between 56319a2 and 166ae22.

📒 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 integration waiver list updates skips for serving, accuracy, hardware, performance, feature, and coverage tests. It also removes obsolete waiver entries.

Changes

Integration test waiver updates

Layer / File(s) Summary
Serving and accuracy waiver entries
tests/integration/test_lists/waives.txt
Adds serving and model accuracy waivers, including LagunaXS, MiniMax, Nemotron, Qwen3.5, and DGX H100 cases. Removes obsolete Qwen3.5 entries.
Hardware and performance waiver entries
tests/integration/test_lists/waives.txt
Removes obsolete hardware-specific waivers and replaces obsolete performance entries with a B200 DeepSeek R1 waiver.
Feature-specific waiver entries
tests/integration/test_lists/waives.txt
Updates visual-generation, KV-cache, attention-backend, scheduler, MoE, Wan, RocketKV, and coverage waivers.

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

Merge Risk: ⚪ Minimal · up to 166ae

This PR only removes two test waivers and does not change product or runtime code. No actionable merge-blocking risk remains; the owner should provide the related test-list and coverage evidence as routine follow-up.

Suggested reviewers: brnguyen2, mzweilz, trtllm-agent

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description leaves the required Description and Test Coverage sections empty and provides no issue, solution, or test details. Add a concise explanation of the issue and solution, and list the relevant tests or CI coverage for the waiver changes.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title follows the required NVBugs and type format and describes the waiver-related test change.
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 files.
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.

@cascade812

Copy link
Copy Markdown
Collaborator Author

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #67553 [ run ] triggered by Bot. Commit: f1f550c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #67553 [ run ] completed with state FAILURE. Commit: f1f550c
/LLM/main/L0_MergeRequest_PR pipeline #55045 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

  • Please check the failed tests and fix your PR
  • If you cannot view the failures, ask the CI triggerer to share details
  • Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

Signed-off-by: Guiju Zhang <7135567+cascade812@users.noreply.github.com>
@cascade812

Copy link
Copy Markdown
Collaborator Author

/bot run

@cascade812

Copy link
Copy Markdown
Collaborator Author

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #67942 [ run ] triggered by Bot. Commit: 56319a2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #67942 [ run ] completed with state SUCCESS. Commit: 56319a2
/LLM/main/L0_MergeRequest_PR pipeline #55397 completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ Action Required:

  • Please check the failed tests and fix your PR
  • If you cannot view the failures, ask the CI triggerer to share details
  • Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

Signed-off-by: Guiju Zhang <7135567+cascade812@users.noreply.github.com>
@cascade812

Copy link
Copy Markdown
Collaborator Author

/bot run --skip "verified by PR "

@cascade812
cascade812 enabled auto-merge (squash) August 21, 2026 18:54
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #68381 Bot args parsing error: usage: /bot [-h]
{run,kill,skip,submit,reviewers,reuse-pipeline,reuse-review} ...
/bot: error: unrecognized arguments: verified by PR

Link to invocation

@cascade812

Copy link
Copy Markdown
Collaborator Author

/bot skip --comment "verified by #17828 "

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #68386 [ skip ] triggered by Bot. Commit: 166ae22 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #68386 [ skip ] completed with state SUCCESS. Commit: 166ae22
Skipping testing for commit 166ae22

Link to invocation

@cascade812
cascade812 merged commit 828e765 into NVIDIA:main Aug 21, 2026
11 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