# HELP sglang:e2e_request_latency_seconds End-to-end request latency in seconds
# TYPE sglang:e2e_request_latency_seconds histogram
sglang:e2e_request_latency_seconds_bucket{le="1.0",model_name="m"} 120.0
sglang:e2e_request_latency_seconds_bucket{le="4.0",model_name="m"} 700.0
sglang:e2e_request_latency_seconds_bucket{le="+Inf",model_name="m"} 900.0
sglang:e2e_request_latency_seconds_sum{model_name="m"} 3150.0
sglang:e2e_request_latency_seconds_count{model_name="m"} 900.0
# TYPE sglang:num_running_reqs gauge
sglang:num_running_reqs{model_name="m"} 22.0
# TYPE sglang:num_queue_reqs gauge
sglang:num_queue_reqs{model_name="m"} 5.0
# TYPE sglang:cache_hit_rate gauge
sglang:cache_hit_rate{model_name="m"} 38.5
