vllm - 💡(How to fix) Fix [CI Failure]: mi325_2: Distributed Compile + RPC Tests (2 GPUs) [1 participants]

TL;DR

• Investigate the mi325_2: Distributed Compile + RPC Tests (2 GPUs) test group to identify the cause of the failure.

Guidance

• Review the test results from the latest nightly build (amd-ci #7854) to understand the nature of the failure.
• Check the hardware status of mi325_2 to ensure there are no underlying hardware issues contributing to the test failure.
• Analyze the test history to see if there are any patterns or correlations between test failures and specific hardware or software configurations.
• Investigate the sync_ready_tickets.py script to ensure it is correctly managing the test group and not introducing any issues.

Notes

• The issue appears to be related to a specific test group and hardware configuration, so the solution may involve modifying the test or hardware setup.
• Without more information about the test failure, it is difficult to provide a more specific solution.

Recommendation

• Apply workaround: Investigate and address the root cause of the test failure in the mi325_2: Distributed Compile + RPC Tests (2 GPUs) test group, as it has failed multiple times in the recent past.