In vLLM v0.23.0, `vllm:kv_cache_usage_perc` is a Prometheus gauge for KV-cache usage where 1 means 100 percent usage.

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

Metric

kv_cache_usage_perc

Applies when

PrometheusStatLogger metrics publisherV1 metrics

Evidence

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:519-527)

definesprimarysource_codecode_introspection

Does not establish

how much free KV cache remains for a specific model
whether a workload will preempt
a universal alert threshold

Guards

vllm_version = v0.23.0
metric_name = vllm:kv_cache_usage_perc
runtime_component = scheduler

Freshness

Pinned release-tag source snapshot; re-check if target phase-1 release changes or metrics API compatibility becomes customer-facing.