In vLLM v0.23.0, `vllm:e2e_request_latency_seconds` is computed when a request enters finished-request accounting using current time minus `arrival_time`.

MetricvLLM v0.23.0confidence: highverified 10 hr agoverified-code

PrometheusStatLoggerV1 metrics

vLLM v0.23.0 v1 metrics stats.py(vllm/v1/metrics/loggers.py:430-475)

definesprimarysource_codecode_introspection

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

In vLLM v0.23.0, vllm:e2e_request_latency_seconds is computed when a request enters finished-request accounting using current time minus arrival_time.