vllm - 💡(How to fix) Fix [CI Failure]: mi355_2: LM Eval Qwen3-5 Models (B200-MI355) [1 comments, 2 participants]

TL;DR

Investigate the mi355_2 hardware status and recent changes to identify the cause of the failing test group.

Guidance

• Review the build logs from amd-ci #7854 to identify any errors or warnings related to the mi355_2 hardware.
• Check the sync_ready_tickets.py script for any recent changes that may be contributing to the test group failures.
• Verify that the mi355_2 hardware is properly configured and functioning correctly.
• Investigate the 5 pass-fail flips in the 60-day window to identify any patterns or correlations with other changes or events.

Notes

The issue lacks detailed information about the test group and the errors encountered, so a thorough investigation of the build logs and hardware status is necessary to determine the root cause.

Recommendation

Apply workaround: Investigate and address the mi355_2 hardware issues, as it is the most likely cause of the failing test group, and then re-run the test to verify the fix.