Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [CI Failure]: mi250_1: V1 Core + KV + Metrics [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#40476•Fetched 2026-04-22 07:45:21
View on GitHub
Comments
0
Participants
1
Timeline
7
Reactions
0
Author
AndreasKaratzasAndreasKaratzas
Participants
AndreasKaratzasAndreasKaratzas
Timeline (top)
project_v2_item_status_changed ×3added_to_project_v2 ×2closed ×1labeled ×1
RAW_BUFFERClick to expand / collapse

AMD nightly — failing test group

Group: mi250_1: V1 Core + KV + Metrics

Current streak start: 2026-04-21 First failure in 60d window: 2026-04-21 Last successful nightly: 2026-04-20 Break frequency (60d, pass↔fail flips): 1 Latest nightly date: 2026-04-21 Latest build(s): amd-ci #7854

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-ci-dashboard/actions/runs/24731404470

extent analysis

TL;DR

Investigate the mi250_1: V1 Core + KV + Metrics test group failure on the AMD nightly build to identify the root cause.

Guidance

  • Review the build logs from amd-ci #7854 to identify any error messages or clues related to the test group failure.
  • Check the sync_ready_tickets.py script to understand how it manages the test group and see if there are any issues with the automation.
  • Investigate the hardware status of mi250_1 to determine if there are any hardware-related issues that could be causing the test failure.
  • Compare the test results from the last successful nightly build (2026-04-20) to the current failing build to identify any changes that may have introduced the issue.

Notes

The issue lacks detailed information about the test failure, so further investigation is needed to determine the root cause.

Recommendation

Apply workaround: Investigate and debug the test group failure to identify the root cause and apply a fix, as there is no clear indication of a fixed version available.

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…
#mixed precision#training loop#device allocation#model download#tokenizer error

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

vllm - 💡(How to fix) Fix [CI Failure]: mi250_1: V1 Core + KV + Metrics [1 participants]