Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [CI Failure]: mi250_1: Basic Models Tests (Other) [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#40198•Fetched 2026-04-19 15:06:00
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

Root Cause

  • Flaky test
  • Can reproduce locally
  • Caused by external libraries (e.g. bug in transformers)
RAW_BUFFERClick to expand / collapse

Name of failing test

(command rocm-smi || true) && export VLLM_TEST_GROUP_NAME=mi250_1-basic-models-tests-other && export VLLM_ALLOW_DEPRECATED_BEAM_SEARCH=1 && cd /vllm-workspace/tests && pytest -v -s models/test_terratorch.py models/test_transformers.py models/test_registry.py

Basic information

  • Flaky test
  • Can reproduce locally
  • Caused by external libraries (e.g. bug in transformers)

🧪 Describe the failing test

  • Latest nightly date: 2026-04-22
  • Latest build(s): amd-ci #7880
  • Latest hardware status: mi250_1=fail

📝 History of failing test

  • Current streak start: 2026-04-16
  • First failure in 60d window: 2026-04-16
  • Last successful nightly: 2026-04-15

extent analysis

TL;DR

  • Investigate the mi250_1: Basic Models Tests (Other) group to identify the cause of the failing test.

Guidance

  • Review the test logs and results from the latest nightly build (#7744) to determine the specific test cases that are failing.
  • Check the hardware status of mi250_1 to ensure it is functioning correctly and not causing the test failures.
  • Analyze the changes made in the latest build to see if any recent updates could be contributing to the test failures.
  • Verify that the sync_ready_tickets.py script is correctly configured and running as expected.

Notes

  • The issue seems to be related to a specific test group and hardware configuration, so the solution may involve identifying a compatibility issue or a problem with the test cases themselves.
  • Without more information about the test failures, it's difficult to provide a more specific solution.

Recommendation

  • Apply workaround: Investigate and address the root cause of the test failures in the mi250_1: Basic Models Tests (Other) group, as this will likely resolve the issue.

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…
#memory optimization#batch processing#GPU compatibility#latency issue#model loading

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: Basic Models Tests (Other) [2 comments, 1 participants]