vLLM Metrics Dashboard
v{{ VERSION }}
Connecting...
30m
2h
8h
24h
3d
7d
30d
Smooth
Running Requests
-
Waiting Requests
-
Output Tokens/s
-
Input Tokens/s
-
Queue Time
-
Avg Prompt Len
-
Avg Gen Len
-
Uptime
-
Failure Rate
-
Running Requests
Waiting Requests
Per-Engine Running Requests
Output Tokens / second
Input Tokens / second
KV Cache Usage (%)
Cache Hit Rate (%)
Failure Rate (%)
Queue Time (s)
Latency (TTFT / ITL / E2E)
Avg Prompt Length
Avg Generation Length
Engine Details
Engine
Running
Waiting
KV Cache
Prompt Tokens
Gen Tokens
Loading...