In vLLM v0.23.0, `vllm:request_prefill_kv_computed_tokens` compare distributions under matched workloads; use cached-token counters as companions and do not treat one bucket count as token throughput.

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

PrometheusStatLoggerV1 metrics

vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:1179-1213)

supportsprimarysource_codecode_introspection

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

In vLLM v0.23.0, vllm:request_prefill_kv_computed_tokens compare distributions under matched workloads; use cached-token counters as companions and do not treat one bucket count as token throughput.