vLLM running-request gauge
vllm · gauge
Fields
id
metric-exposures/w3m-vllm-vllm-num-requests-runningMetric name
vllm:num_requests_running
Metric type
gauge
Unit
requests
Exposure
prometheus
Endpoint
:8000/metrics
Labels
model_nameengine
Enabled by default
yes
notes
vLLM main, PrometheusStatLogger in vllm/v1/metrics/loggers.py, read 2026-10-04. On by default (EngineArgs.disable_log_stats defaults False); served at :8000/metrics. Bucket family name in --custom-histogram-buckets: no bucket family. 'Number of requests in model execution batches.' Set every logging interval (default 10s), so it is a sampled level, not an event count. multiprocess_mode='mostrecent'.
Notes
vLLM main, PrometheusStatLogger in vllm/v1/metrics/loggers.py, read 2026-10-04. On by default (EngineArgs.disable_log_stats defaults False); served at :8000/metrics. Bucket family name in --custom-histogram-buckets: no bucket family. 'Number of requests in model execution batches.' Set every logging interval (default 10s), so it is a sampled level, not an event count. multiprocess_mode='mostrecent'.