Schema.ai· vLLM
vLLM v0.23.0API up

vllm:spec_decode_num_accepted_tokens_per_pos

Counter for accepted speculative tokens per draft position, labeled by position.

MetricPrometheusvLLM v0.23.0verified Jul 9

Claims (0)

No claims about this entity yet.

Availability

vllm:spec_decode_num_accepted_tokens_per_pos is registered as a Prometheus counter in vLLM v0.23.0. Registration requires speculative_config is not None.
vllm.surface.prometheus_metricscomplete_inventoryPrometheusStatLogger metrics publisherspeculative_config is not None

vLLM v0.23.0 v1 spec_decode metrics.py · vllm/v1/spec_decode/metrics.py:181-198