In vLLM v0.23.0, `vllm:prefix_cache_hits` divide same-window hit and query rates; no universal healthy percentage follows because reuse is workload-dependent.

MetricvLLM v0.23.0confidence: highverified 11 hr agoverified-docs

PrometheusStatLoggerV1 metrics

supportsprimarydocumentationdocs_extraction

Pinned release-tag semantics; do not carry to another version without continuity evidence.

In vLLM v0.23.0, vllm:prefix_cache_hits divide same-window hit and query rates; no universal healthy percentage follows because reuse is workload-dependent.