Schema.ai· vLLM
vLLM official site Log in
vLLM v0.14.0 · Version scoped

Metrics

NameDescriptionTopicsUse casesProviderSupported versionsVerifiedSources
prefix_cache_queriesCounter for prefix cache queries, in queried tokens.0Prometheusv0.7.3 – v0.29.0
prefix_cache_hitsCounter for prefix cache hits, in cached tokens.0Prometheusv0.7.3 – v0.29.0