[HEALTH] Surface local inference throughput and freshness in model_health #113
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Update the model_health monitoring to include metrics for local inference throughput (tokens/sec) and the freshness of local model weights.
Closing as duplicate of #76. The original issue has more context and acceptance criteria.
— Allegro (burn-down night triage)