Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [CI Failure]: mi250_1: Multi-Modal Accuracy Eval (Small Models) [2 comments, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
vllm-project/vllm#40201•Fetched 2026-04-19 15:05:56
View on GitHub
Comments
2
Participants
1
Timeline
6
Reactions
0
Author
AndreasKaratzasAndreasKaratzas
Participants
AndreasKaratzasAndreasKaratzas
Timeline (top)
added_to_project_v2 ×2commented ×2labeled ×1project_v2_item_status_changed ×1
RAW_BUFFERClick to expand / collapse

AMD nightly — failing test group

Group: mi250_1: Multi-Modal Accuracy Eval (Small Models)

Current streak start: 2026-04-16 First failure in 60d window: 2026-03-31 Last successful nightly: 2026-04-15 Break frequency (60d, pass↔fail flips): 4 Latest nightly date: 2026-04-18 Latest build(s): #7791

Hardware status in latest nightly

hardwarestatus
mi250_1fail

Auto-managed by sync_ready_tickets.py. Closed + moved to Done when this group passes on all AMD hardware.

Last sync: https://github.com/AndreasKaratzas/vllm-internal-project-dashboard/actions/runs/24602867596

extent analysis

TL;DR

Investigate the mi250_1 hardware status and recent changes to identify the cause of the failing Multi-Modal Accuracy Eval (Small Models) test group.

Guidance

  • Review the hardware status and test results for mi250_1 to determine if there are any patterns or correlations with the test failures.
  • Check the build history and changes made between the last successful nightly (2026-04-15) and the first failure in the 60-day window (2026-03-31) to identify potential causes.
  • Investigate the sync_ready_tickets.py script and its role in managing the test group to ensure it is not contributing to the failures.
  • Analyze the test group's configuration and dependencies to determine if there are any versioning or compatibility issues that could be causing the failures.

Notes

The issue lacks detailed information about the test group's configuration, code, and dependencies, making it challenging to provide a more specific solution.

Recommendation

Apply workaround: Investigate and address the mi250_1 hardware status and recent changes to identify the root cause of the failing test group, as the issue seems to be related to a specific hardware or test configuration.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#environment setup#docker error#permission error#memory optimization#batch processing

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING