In vLLM v0.23.0, vllm:request_decode_time_seconds is registered with the label names model_name, engine.
MetricvLLM v0.23.0confidence: highverified 1 hr agoverified-code
Metric
request_decode_time_secondsApplies when
PrometheusStatLogger metrics publisherV1 metrics
Evidence
vLLM v0.23.0 v1 metrics loggers.py(vllm/v1/metrics/loggers.py:910-915)
definesprimarysource_codecode_introspection
Does not establish
- the set of values any of these labels takes at runtime
- label cardinality in a deployment
Guards
vllm_version= v0.23.0metric_name=vllm:request_decode_time_seconds