# HELP sglang:new_seq Number of new sequences
# TYPE sglang:new_seq gauge
sglang:new_seq{name="google/gemma-2-9b-it"} 50.0
# HELP sglang:new_token Number of new token
# TYPE sglang:new_token gauge
sglang:new_token{name="google/gemma-2-9b-it"} 153.0
# HELP sglang:cached_token Number of cached token
# TYPE sglang:cached_token gauge
sglang:cached_token{name="google/gemma-2-9b-it"} 6252.0
# HELP sglang:cache_hit_rate Cache hit rate
# TYPE sglang:cache_hit_rate gauge
sglang:cache_hit_rate{name="google/gemma-2-9b-it"} 87.58777633289988
# HELP sglang:queue_req Number of queue requests
# TYPE sglang:queue_req gauge
sglang:queue_req{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:num_requests_running Number of requests currently running on GPU
# TYPE sglang:num_requests_running gauge
sglang:num_requests_running{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:num_requests_waiting Number of requests waiting to be processed.
# TYPE sglang:num_requests_waiting gauge
sglang:num_requests_waiting{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:gen_throughput Gen token throughput (token/s)
# TYPE sglang:gen_throughput gauge
sglang:gen_throughput{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:token_usage Total token usage
# TYPE sglang:token_usage gauge
sglang:token_usage{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:max_total_num_tokens Maximum total number of tokens
# TYPE sglang:max_total_num_tokens gauge
sglang:max_total_num_tokens{name="google/gemma-2-9b-it"} 161723.0
# HELP sglang:max_prefill_tokens Maximum prefill tokens
# TYPE sglang:max_prefill_tokens gauge
sglang:max_prefill_tokens{name="google/gemma-2-9b-it"} 16384.0
# HELP sglang:max_running_requests Maximum running requests
# TYPE sglang:max_running_requests gauge
sglang:max_running_requests{name="google/gemma-2-9b-it"} 4097.0
# HELP sglang:context_len Context length
# TYPE sglang:context_len gauge
sglang:context_len{name="google/gemma-2-9b-it"} 8192.0
# HELP sglang:request_prompt_tokens Number of prefill tokens processed
# TYPE sglang:request_prompt_tokens histogram
sglang:request_prompt_tokens_sum{name="google/gemma-2-9b-it"} 1129.0
sglang:request_prompt_tokens_bucket{le="1.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_prompt_tokens_bucket{le="2.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_prompt_tokens_bucket{le="5.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_prompt_tokens_bucket{le="10.0",name="google/gemma-2-9b-it"} 1.0
sglang:request_prompt_tokens_bucket{le="20.0",name="google/gemma-2-9b-it"} 1.0
sglang:request_prompt_tokens_bucket{le="50.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="100.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="200.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="500.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="1000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="2000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="5000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="10000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="20000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="50000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="100000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_bucket{le="+Inf",name="google/gemma-2-9b-it"} 51.0
sglang:request_prompt_tokens_count{name="google/gemma-2-9b-it"} 51.0
# HELP sglang:request_generation_tokens Number of generation tokens processed.
# TYPE sglang:request_generation_tokens histogram
sglang:request_generation_tokens_sum{name="google/gemma-2-9b-it"} 5341.0
sglang:request_generation_tokens_bucket{le="1.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_generation_tokens_bucket{le="2.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_generation_tokens_bucket{le="5.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_generation_tokens_bucket{le="10.0",name="google/gemma-2-9b-it"} 1.0
sglang:request_generation_tokens_bucket{le="20.0",name="google/gemma-2-9b-it"} 1.0
sglang:request_generation_tokens_bucket{le="50.0",name="google/gemma-2-9b-it"} 1.0
sglang:request_generation_tokens_bucket{le="100.0",name="google/gemma-2-9b-it"} 1.0
sglang:request_generation_tokens_bucket{le="200.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="500.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="1000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="2000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="5000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="10000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="20000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="50000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="100000.0",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_bucket{le="+Inf",name="google/gemma-2-9b-it"} 51.0
sglang:request_generation_tokens_count{name="google/gemma-2-9b-it"} 51.0