vllm - 💡(How to fix) Fix [CI Failure]: mi325_1: V1 Spec Decode [2 comments, 1 participants]

TL;DR

Investigate the mi325_1: V1 Spec Decode test group to identify the cause of the failure in the AMD nightly builds.

Guidance

• Review the test results and logs from the latest nightly build (#7791) to understand the nature of the failure in the mi325_1: V1 Spec Decode test group.
• Check the hardware status of mi325_1 to ensure it is functioning correctly and not contributing to the test failure.
• Compare the test results from the last successful nightly build (2026-04-15) with the latest failed build (2026-04-18) to identify any changes that may have caused the failure.
• Investigate any recent code changes or updates that may be related to the mi325_1: V1 Spec Decode test group and verify if they are the cause of the failure.

Notes

The issue seems to be related to a specific test group and hardware configuration, so the investigation should focus on these areas. The fact that the test group was passing previously and started failing recently suggests that a recent change may be the cause.

Recommendation

Apply workaround: Investigate and fix the root cause of the test failure, as it is likely related to a recent change or update.