vllm - 💡(How to fix) Fix [CI Failure]: mi325_1: Kernels MoE Test %N [2 comments, 1 participants]

TL;DR

Investigate the mi325_1: Kernels MoE Test %N group to identify the cause of the failing test.

Guidance

• Review the test logs and output from the mi325_1 hardware to understand the failure mode.
• Check the sync_ready_tickets.py script for any potential issues or errors that could be contributing to the test failure.
• Verify that the mi325_1 hardware is properly configured and functioning correctly.
• Investigate the changes made in the latest nightly build (#7791) to see if any of them could be causing the test failure.

Notes

The issue lacks detailed information about the test failure, so a thorough investigation of the test logs and hardware configuration is necessary to identify the root cause.

Recommendation

Apply workaround: Investigate and fix the test failure in the mi325_1: Kernels MoE Test %N group, as there is no clear indication of a fixed version available.