Skip to content

[https://nvbugs/6525011][test] Waive TestLagunaXS::test_fp8 on RTXPro6000D - #17661

Merged
brnguyen2 merged 1 commit into
NVIDIA:mainfrom
brnguyen2:user/brnguyen/waive-lagunaxs-fp8-rtxpro6000d
Aug 13, 2026
Merged

[https://nvbugs/6525011][test] Waive TestLagunaXS::test_fp8 on RTXPro6000D#17661
brnguyen2 merged 1 commit into
NVIDIA:mainfrom
brnguyen2:user/brnguyen/waive-lagunaxs-fp8-rtxpro6000d

Conversation

@brnguyen2

@brnguyen2 brnguyen2 commented Aug 13, 2026

Copy link
Copy Markdown
Collaborator

Description

accuracy/test_llm_api_pytorch.py::TestLagunaXS::test_fp8 is already waived on full:B200 and full:B300 under nvbugs/6525011 (CUDA-graph runner not holding a strong ref to graph outputs → illegal memory access during generation CUDA-graph warmup on the TRT-LLM Gen FP8 MoE path). The same failure now reproduces on RTXPro6000D (Blackwell, SM120), which was not covered by the existing waivers, so the test breaks pre-merge L0 on that stage (observed on PR CI run L0_MergeRequest_PR #53409, unrelated to that PR).

This extends the existing waiver to full:RTXPro6000D, citing the same bug.

Scope note: the test also runs on H100 (Hopper/SM90), but there is no failure evidence there and the faulting kernel is Blackwell-gen FP8 MoE, so H100 is intentionally left unwaived to preserve coverage.

Test Coverage

Waive-only change; no new tests. Removes one known-failing test from the RTXPro6000D pre-merge stage.

PR Checklist

  • PR title follows [JIRA/NVBUG/None][type] description
  • Commit is DCO signed-off
  • Waiver references a tracking NVBug (nvbugs/6525011)

Dev Engineer Review

  • Added one waiver for TestLagunaXS::test_fp8 on full:RTXPro6000D.
  • Referenced nvbugs/6525011, consistent with existing waivers.
  • Scope is limited to tests/integration/test_lists/waives.txt.
  • No code, API, performance, or error-handling changes.
  • No duplicate waiver or invalid test path is indicated.

QA Engineer Review

  • Modified tests/integration/test_lists/waives.txt.
  • Added the RTXPro6000D waiver entry.
  • No test-db/ or qa/ files were modified.
  • Verdict: needs follow-up because CBTS coverage data is unavailable.

…6000D

The CUDA-graph FP8-MoE illegal-memory-access failure tracked in
nvbugs/6525011 (already waived on full:B200 and full:B300) also
reproduces on RTXPro6000D. Extend the same waiver to that platform.

Signed-off-by: Brian Nguyen <brnguyen@nvidia.com>
@brnguyen2
brnguyen2 marked this pull request as ready for review August 13, 2026 22:22
@brnguyen2

Copy link
Copy Markdown
Collaborator Author

/bot skip --comment "waive only PR"

@coderabbitai

coderabbitai Bot commented Aug 13, 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: 48a5d256-0b49-4234-9c27-b5cd981ded81

📥 Commits

Reviewing files that changed from the base of the PR and between 86dbc1c and 5febb1c.

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

Walkthrough

The waiver list skips TestLagunaXS::test_fp8 on RTXPro6000D and references nvbugs 6525011.

Changes

Test waiver

Layer / File(s) Summary
RTXPro6000D FP8 waiver
tests/integration/test_lists/waives.txt
Adds a skip entry for TestLagunaXS::test_fp8 on RTXPro6000D.

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

Mergeability Score: ⚪ Minimal · up to 5febb

This is a localized waiver-only change with no production behavior impact. No actionable merge-blocking risk remains beyond normal checks and review.

Possibly related PRs

Suggested reviewers: bowenfu

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies the tracking bug, change type, test, and RTXPro6000D platform waiver.
Description check ✅ Passed The description explains the issue, scope, rationale, test coverage, and relevant checklist items for this waiver-only change.
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.

@brnguyen2

Copy link
Copy Markdown
Collaborator Author

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #66065 [ skip ] triggered by Bot. Commit: 5febb1c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #66069 [ run ] triggered by Bot. Commit: 5febb1c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #66065 [ skip ] completed with state ABORTED. Commit: 5febb1c

Link to invocation

@brnguyen2

Copy link
Copy Markdown
Collaborator Author

/bot skip --comment "waive only PR"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #66074 [ skip ] triggered by Bot. Commit: 5febb1c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github/17661-5febb1c #66069 was force-killed by a newer pipeline run.
L0 job information not available (job may not have been triggered yet).

Link to superseding invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #66074 [ skip ] completed with state SUCCESS. Commit: 5febb1c
Skipping testing for commit 5febb1c

Link to invocation

@brnguyen2
brnguyen2 merged commit a611a65 into NVIDIA:main Aug 13, 2026
14 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