vLLM waiting-request gauge
vllm · gauge
Fields
id
metric-exposures/w3m-vllm-vllm-num-requests-waitingMetric name
vllm:num_requests_waiting
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. The undifferentiated waiting count; see vllm:num_requests_waiting_by_reason for the split that says WHY. 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. The undifferentiated waiting count; see vllm:num_requests_waiting_by_reason for the split that says WHY. multiprocess_mode='mostrecent'.