vllm - 💡(How to fix) Fix [CI Failure]: mi355_1: Language Models Test (Extended Generation) [2 comments, 1 participants]

TL;DR

Investigate the mi355_1 hardware status and Language Models Test (Extended Generation) to identify the cause of the failing test group.

Guidance

• Review the test results for mi355_1: Language Models Test (Extended Generation) to understand the nature of the failure.
• Check the hardware status of mi355_1 to determine if there are any underlying issues that could be contributing to the test failures.
• Investigate the changes made in the latest nightly build (#7791) to see if any of them could be causing the test failures.
• Verify that the sync_ready_tickets.py script is functioning correctly and not causing any issues with the test group.

Notes

The issue lacks detailed information about the test failures, so it's difficult to provide a more specific solution. Further investigation is needed to determine the root cause of the issue.

Recommendation

Apply workaround: Investigate and address the underlying issues with the mi355_1 hardware and Language Models Test (Extended Generation) to prevent future test failures.