vLLM Metrics Dashboard
v0.1.0
Connecting...
15m
1h
6h
24h
Running Requests
-
Waiting Requests
-
KV Cache
-
Requests/s
-
Output Tokens/s
-
Cache Hit Rate
-
Total Requests
-
Uptime
-
Running Requests
Waiting Requests
Requests / second
Output Tokens / second
Input Tokens / second
KV Cache Usage (%)
Cache Hit Rate (%)
Latency (TTFT / ITL / E2E)
Per-Engine Running Requests
Engine Details
Engine
Running
Waiting
KV Cache
Prompt Tokens
Gen Tokens
Loading...