# HELP python_gc_objects_collected_total Objects collected during gc # TYPE python_gc_objects_collected_total counter python_gc_objects_collected_total{generation="0"} 59597.0 python_gc_objects_collected_total{generation="1"} 7099.0 python_gc_objects_collected_total{generation="2"} 1256.0 # HELP python_gc_objects_uncollectable_total Uncollectable objects found during GC # TYPE python_gc_objects_uncollectable_total counter python_gc_objects_uncollectable_total{generation="0"} 0.0 python_gc_objects_uncollectable_total{generation="1"} 0.0 python_gc_objects_uncollectable_total{generation="2"} 0.0 # HELP python_gc_collections_total Number of times this generation was collected # TYPE python_gc_collections_total counter python_gc_collections_total{generation="0"} 4511.0 python_gc_collections_total{generation="1"} 410.0 python_gc_collections_total{generation="2"} 15.0 # HELP python_info Python platform information # TYPE python_info gauge python_info{implementation="CPython",major="3",minor="10",patchlevel="12",version="3.10.12"} 1.0 # HELP process_virtual_memory_bytes Virtual memory size in bytes. # TYPE process_virtual_memory_bytes gauge process_virtual_memory_bytes 7.562072064e+09 # HELP process_resident_memory_bytes Resident memory size in bytes. # TYPE process_resident_memory_bytes gauge process_resident_memory_bytes 1.165881344e+09 # HELP process_start_time_seconds Start time of the process since unix epoch in seconds. # TYPE process_start_time_seconds gauge process_start_time_seconds 1.79124141275e+09 # HELP process_cpu_seconds_total Total user and system CPU time spent in seconds. # TYPE process_cpu_seconds_total counter process_cpu_seconds_total 15.66 # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge process_open_fds 35.0 # HELP process_max_fds Maximum number of open file descriptors. # TYPE process_max_fds gauge process_max_fds 65535.0 # HELP vllm:spec_decode_num_drafts_total Number of spec decoding drafts. # TYPE vllm:spec_decode_num_drafts_total counter vllm:spec_decode_num_drafts_total{engine="0",model_name="google/gemma-4-12B-it"} 12022.0 # HELP vllm:spec_decode_num_drafts_created Number of spec decoding drafts. # TYPE vllm:spec_decode_num_drafts_created gauge vllm:spec_decode_num_drafts_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885344176e+09 # HELP vllm:spec_decode_num_draft_tokens_total Number of draft tokens. # TYPE vllm:spec_decode_num_draft_tokens_total counter vllm:spec_decode_num_draft_tokens_total{engine="0",model_name="google/gemma-4-12B-it"} 60110.0 # HELP vllm:spec_decode_num_draft_tokens_created Number of draft tokens. # TYPE vllm:spec_decode_num_draft_tokens_created gauge vllm:spec_decode_num_draft_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488534432e+09 # HELP vllm:spec_decode_num_accepted_tokens_total Number of accepted tokens. # TYPE vllm:spec_decode_num_accepted_tokens_total counter vllm:spec_decode_num_accepted_tokens_total{engine="0",model_name="google/gemma-4-12B-it"} 44493.0 # HELP vllm:spec_decode_num_accepted_tokens_created Number of accepted tokens. # TYPE vllm:spec_decode_num_accepted_tokens_created gauge vllm:spec_decode_num_accepted_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885344443e+09 # HELP vllm:spec_decode_num_accepted_tokens_per_pos_total Accepted tokens per draft position. # TYPE vllm:spec_decode_num_accepted_tokens_per_pos_total counter vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="google/gemma-4-12B-it",position="0"} 10905.0 vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="google/gemma-4-12B-it",position="1"} 9841.0 vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="google/gemma-4-12B-it",position="2"} 8851.0 vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="google/gemma-4-12B-it",position="3"} 7913.0 vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="google/gemma-4-12B-it",position="4"} 6983.0 # HELP vllm:spec_decode_num_accepted_tokens_per_pos_created Accepted tokens per draft position. # TYPE vllm:spec_decode_num_accepted_tokens_per_pos_created gauge vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="google/gemma-4-12B-it",position="0"} 1.7912414885344608e+09 vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="google/gemma-4-12B-it",position="1"} 1.7912414885344656e+09 vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="google/gemma-4-12B-it",position="2"} 1.7912414885344691e+09 vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="google/gemma-4-12B-it",position="3"} 1.7912414885344727e+09 vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="google/gemma-4-12B-it",position="4"} 1.7912414885344756e+09 # HELP vllm:num_requests_running Number of requests in model execution batches. # TYPE vllm:num_requests_running gauge vllm:num_requests_running{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:num_requests_waiting Number of requests waiting to be processed. # TYPE vllm:num_requests_waiting gauge vllm:num_requests_waiting{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:engine_sleep_state Engine sleep state; awake = 0 means engine is sleeping; awake = 1 means engine is awake; weights_offloaded = 1 means sleep level 1; discard_all = 1 means sleep level 2. # TYPE vllm:engine_sleep_state gauge vllm:engine_sleep_state{engine="0",model_name="google/gemma-4-12B-it",sleep_state="awake"} 1.0 vllm:engine_sleep_state{engine="0",model_name="google/gemma-4-12B-it",sleep_state="weights_offloaded"} 0.0 vllm:engine_sleep_state{engine="0",model_name="google/gemma-4-12B-it",sleep_state="discard_all"} 0.0 # HELP vllm:kv_cache_usage_perc KV-cache usage. 1 means 100 percent usage. # TYPE vllm:kv_cache_usage_perc gauge vllm:kv_cache_usage_perc{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:prefix_cache_queries_total Prefix cache queries, in terms of number of queried tokens. # TYPE vllm:prefix_cache_queries_total counter vllm:prefix_cache_queries_total{engine="0",model_name="google/gemma-4-12B-it"} 19564.0 # HELP vllm:prefix_cache_queries_created Prefix cache queries, in terms of number of queried tokens. # TYPE vllm:prefix_cache_queries_created gauge vllm:prefix_cache_queries_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488534571e+09 # HELP vllm:prefix_cache_hits_total Prefix cache hits, in terms of number of cached tokens. # TYPE vllm:prefix_cache_hits_total counter vllm:prefix_cache_hits_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:prefix_cache_hits_created Prefix cache hits, in terms of number of cached tokens. # TYPE vllm:prefix_cache_hits_created gauge vllm:prefix_cache_hits_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885345793e+09 # HELP vllm:external_prefix_cache_queries_total External prefix cache queries from KV connector cross-instance cache sharing, in terms of number of queried tokens. # TYPE vllm:external_prefix_cache_queries_total counter vllm:external_prefix_cache_queries_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:external_prefix_cache_queries_created External prefix cache queries from KV connector cross-instance cache sharing, in terms of number of queried tokens. # TYPE vllm:external_prefix_cache_queries_created gauge vllm:external_prefix_cache_queries_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885345871e+09 # HELP vllm:external_prefix_cache_hits_total External prefix cache hits from KV connector cross-instance cache sharing, in terms of number of cached tokens. # TYPE vllm:external_prefix_cache_hits_total counter vllm:external_prefix_cache_hits_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:external_prefix_cache_hits_created External prefix cache hits from KV connector cross-instance cache sharing, in terms of number of cached tokens. # TYPE vllm:external_prefix_cache_hits_created gauge vllm:external_prefix_cache_hits_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885345948e+09 # HELP vllm:mm_cache_queries_total Multi-modal cache queries, in terms of number of queried items. # TYPE vllm:mm_cache_queries_total counter vllm:mm_cache_queries_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:mm_cache_queries_created Multi-modal cache queries, in terms of number of queried items. # TYPE vllm:mm_cache_queries_created gauge vllm:mm_cache_queries_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885346017e+09 # HELP vllm:mm_cache_hits_total Multi-modal cache hits, in terms of number of cached items. # TYPE vllm:mm_cache_hits_total counter vllm:mm_cache_hits_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:mm_cache_hits_created Multi-modal cache hits, in terms of number of cached items. # TYPE vllm:mm_cache_hits_created gauge vllm:mm_cache_hits_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488534608e+09 # HELP vllm:num_preemptions_total Cumulative number of preemption from the engine. # TYPE vllm:num_preemptions_total counter vllm:num_preemptions_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:num_preemptions_created Cumulative number of preemption from the engine. # TYPE vllm:num_preemptions_created gauge vllm:num_preemptions_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488534614e+09 # HELP vllm:prompt_tokens_total Number of prefill tokens processed. # TYPE vllm:prompt_tokens_total counter vllm:prompt_tokens_total{engine="0",model_name="google/gemma-4-12B-it"} 19564.0 # HELP vllm:prompt_tokens_created Number of prefill tokens processed. # TYPE vllm:prompt_tokens_created gauge vllm:prompt_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.79124148853462e+09 # HELP vllm:prompt_tokens_by_source_total Number of prompt tokens by source. # TYPE vllm:prompt_tokens_by_source_total counter vllm:prompt_tokens_by_source_total{engine="0",model_name="google/gemma-4-12B-it",source="local_compute"} 19564.0 vllm:prompt_tokens_by_source_total{engine="0",model_name="google/gemma-4-12B-it",source="local_cache_hit"} 0.0 vllm:prompt_tokens_by_source_total{engine="0",model_name="google/gemma-4-12B-it",source="external_kv_transfer"} 0.0 # HELP vllm:prompt_tokens_by_source_created Number of prompt tokens by source. # TYPE vllm:prompt_tokens_by_source_created gauge vllm:prompt_tokens_by_source_created{engine="0",model_name="google/gemma-4-12B-it",source="local_compute"} 1.7912414885346286e+09 vllm:prompt_tokens_by_source_created{engine="0",model_name="google/gemma-4-12B-it",source="local_cache_hit"} 1.7912414885346324e+09 vllm:prompt_tokens_by_source_created{engine="0",model_name="google/gemma-4-12B-it",source="external_kv_transfer"} 1.7912414885346358e+09 # HELP vllm:prompt_tokens_cached_total Number of cached prompt tokens (local + external). # TYPE vllm:prompt_tokens_cached_total counter vllm:prompt_tokens_cached_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:prompt_tokens_cached_created Number of cached prompt tokens (local + external). # TYPE vllm:prompt_tokens_cached_created gauge vllm:prompt_tokens_cached_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885346427e+09 # HELP vllm:prompt_tokens_recomputed_total Number of cached tokens recomputed for forward pass. # TYPE vllm:prompt_tokens_recomputed_total counter vllm:prompt_tokens_recomputed_total{engine="0",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:prompt_tokens_recomputed_created Number of cached tokens recomputed for forward pass. # TYPE vllm:prompt_tokens_recomputed_created gauge vllm:prompt_tokens_recomputed_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885346498e+09 # HELP vllm:generation_tokens_total Number of generation tokens processed. # TYPE vllm:generation_tokens_total counter vllm:generation_tokens_total{engine="0",model_name="google/gemma-4-12B-it"} 56715.0 # HELP vllm:generation_tokens_created Number of generation tokens processed. # TYPE vllm:generation_tokens_created gauge vllm:generation_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885346568e+09 # HELP vllm:request_success_total Count of successfully processed requests. # TYPE vllm:request_success_total counter vllm:request_success_total{engine="0",finished_reason="stop",model_name="google/gemma-4-12B-it"} 194.0 vllm:request_success_total{engine="0",finished_reason="length",model_name="google/gemma-4-12B-it"} 6.0 vllm:request_success_total{engine="0",finished_reason="abort",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_success_total{engine="0",finished_reason="error",model_name="google/gemma-4-12B-it"} 0.0 # HELP vllm:request_success_created Count of successfully processed requests. # TYPE vllm:request_success_created gauge vllm:request_success_created{engine="0",finished_reason="stop",model_name="google/gemma-4-12B-it"} 1.7912414885346751e+09 vllm:request_success_created{engine="0",finished_reason="length",model_name="google/gemma-4-12B-it"} 1.7912414885346801e+09 vllm:request_success_created{engine="0",finished_reason="abort",model_name="google/gemma-4-12B-it"} 1.7912414885346837e+09 vllm:request_success_created{engine="0",finished_reason="error",model_name="google/gemma-4-12B-it"} 1.7912414885346878e+09 # HELP vllm:request_prompt_tokens Number of prefill tokens processed. # TYPE vllm:request_prompt_tokens histogram vllm:request_prompt_tokens_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prompt_tokens_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prompt_tokens_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prompt_tokens_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prompt_tokens_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prompt_tokens_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prompt_tokens_bucket{engine="0",le="100.0",model_name="google/gemma-4-12B-it"} 126.0 vllm:request_prompt_tokens_bucket{engine="0",le="200.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="500.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="1000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="2000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="5000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="10000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="20000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="50000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="100000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="200000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prompt_tokens_sum{engine="0",model_name="google/gemma-4-12B-it"} 19564.0 # HELP vllm:request_prompt_tokens_created Number of prefill tokens processed. # TYPE vllm:request_prompt_tokens_created gauge vllm:request_prompt_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885347178e+09 # HELP vllm:request_generation_tokens Number of generation tokens processed. # TYPE vllm:request_generation_tokens histogram vllm:request_generation_tokens_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_generation_tokens_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_generation_tokens_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_generation_tokens_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_generation_tokens_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_generation_tokens_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_generation_tokens_bucket{engine="0",le="100.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_generation_tokens_bucket{engine="0",le="200.0",model_name="google/gemma-4-12B-it"} 35.0 vllm:request_generation_tokens_bucket{engine="0",le="500.0",model_name="google/gemma-4-12B-it"} 194.0 vllm:request_generation_tokens_bucket{engine="0",le="1000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="2000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="5000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="10000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="20000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="50000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="100000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="200000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_generation_tokens_sum{engine="0",model_name="google/gemma-4-12B-it"} 56715.0 # HELP vllm:request_generation_tokens_created Number of generation tokens processed. # TYPE vllm:request_generation_tokens_created gauge vllm:request_generation_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488534753e+09 # HELP vllm:iteration_tokens_total Histogram of number of tokens per engine_step. # TYPE vllm:iteration_tokens_total histogram vllm:iteration_tokens_total_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 1117.0 vllm:iteration_tokens_total_bucket{engine="0",le="8.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:iteration_tokens_total_bucket{engine="0",le="16.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:iteration_tokens_total_bucket{engine="0",le="32.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:iteration_tokens_total_bucket{engine="0",le="64.0",model_name="google/gemma-4-12B-it"} 12024.0 vllm:iteration_tokens_total_bucket{engine="0",le="128.0",model_name="google/gemma-4-12B-it"} 12202.0 vllm:iteration_tokens_total_bucket{engine="0",le="256.0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_bucket{engine="0",le="512.0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_bucket{engine="0",le="1024.0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_bucket{engine="0",le="2048.0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_bucket{engine="0",le="4096.0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_bucket{engine="0",le="8192.0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_bucket{engine="0",le="16384.0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_count{engine="0",model_name="google/gemma-4-12B-it"} 12222.0 vllm:iteration_tokens_total_sum{engine="0",model_name="google/gemma-4-12B-it"} 76279.0 # HELP vllm:iteration_tokens_total_created Histogram of number of tokens per engine_step. # TYPE vllm:iteration_tokens_total_created gauge vllm:iteration_tokens_total_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885348208e+09 # HELP vllm:request_max_num_generation_tokens Histogram of maximum number of requested generation tokens. # TYPE vllm:request_max_num_generation_tokens histogram vllm:request_max_num_generation_tokens_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="100.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="200.0",model_name="google/gemma-4-12B-it"} 35.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="500.0",model_name="google/gemma-4-12B-it"} 194.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="1000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="2000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="5000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="10000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="20000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="50000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="100000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="200000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_max_num_generation_tokens_sum{engine="0",model_name="google/gemma-4-12B-it"} 56715.0 # HELP vllm:request_max_num_generation_tokens_created Histogram of maximum number of requested generation tokens. # TYPE vllm:request_max_num_generation_tokens_created gauge vllm:request_max_num_generation_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488534851e+09 # HELP vllm:request_params_n Histogram of the n request parameter. # TYPE vllm:request_params_n histogram vllm:request_params_n_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_n_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_n_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_n_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_n_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_n_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_n_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_n_sum{engine="0",model_name="google/gemma-4-12B-it"} 200.0 # HELP vllm:request_params_n_created Histogram of the n request parameter. # TYPE vllm:request_params_n_created gauge vllm:request_params_n_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885348752e+09 # HELP vllm:request_params_max_tokens Histogram of the max_tokens request parameter. # TYPE vllm:request_params_max_tokens histogram vllm:request_params_max_tokens_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="100.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="200.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="500.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_params_max_tokens_bucket{engine="0",le="1000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="2000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="5000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="10000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="20000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="50000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="100000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="200000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_params_max_tokens_sum{engine="0",model_name="google/gemma-4-12B-it"} 102400.0 # HELP vllm:request_params_max_tokens_created Histogram of the max_tokens request parameter. # TYPE vllm:request_params_max_tokens_created gauge vllm:request_params_max_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885348961e+09 # HELP vllm:time_to_first_token_seconds Histogram of time to first token in seconds. # TYPE vllm:time_to_first_token_seconds histogram vllm:time_to_first_token_seconds_bucket{engine="0",le="0.001",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.005",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.01",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.02",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.04",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.06",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.08",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.1",model_name="google/gemma-4-12B-it"} 0.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.25",model_name="google/gemma-4-12B-it"} 180.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="0.75",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="7.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="80.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="160.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="640.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="2560.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:time_to_first_token_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 24.1647686958313 # HELP vllm:time_to_first_token_seconds_created Histogram of time to first token in seconds. # TYPE vllm:time_to_first_token_seconds_created gauge vllm:time_to_first_token_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885349178e+09 # HELP vllm:inter_token_latency_seconds Histogram of inter-token latency in seconds. # TYPE vllm:inter_token_latency_seconds histogram vllm:inter_token_latency_seconds_bucket{engine="0",le="0.01",model_name="google/gemma-4-12B-it"} 0.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.025",model_name="google/gemma-4-12B-it"} 0.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.05",model_name="google/gemma-4-12B-it"} 17.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.075",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.1",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.15",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.2",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.3",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.4",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="0.75",model_name="google/gemma-4-12B-it"} 12018.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 12020.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="7.5",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="80.0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 12022.0 vllm:inter_token_latency_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 627.659850189928 # HELP vllm:inter_token_latency_seconds_created Histogram of inter-token latency in seconds. # TYPE vllm:inter_token_latency_seconds_created gauge vllm:inter_token_latency_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885349486e+09 # HELP vllm:request_time_per_output_token_seconds Histogram of time_per_output_token_seconds per request. # TYPE vllm:request_time_per_output_token_seconds histogram vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.01",model_name="google/gemma-4-12B-it"} 19.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.025",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.05",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.075",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.1",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.15",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.2",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.3",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.4",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.75",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="7.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="80.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_time_per_output_token_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 2.201909436440487 # HELP vllm:request_time_per_output_token_seconds_created Histogram of time_per_output_token_seconds per request. # TYPE vllm:request_time_per_output_token_seconds_created gauge vllm:request_time_per_output_token_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488534972e+09 # HELP vllm:e2e_request_latency_seconds Histogram of e2e request latency in seconds. # TYPE vllm:e2e_request_latency_seconds histogram vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.3",model_name="google/gemma-4-12B-it"} 0.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 0.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.8",model_name="google/gemma-4-12B-it"} 0.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.5",model_name="google/gemma-4-12B-it"} 2.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 16.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 56.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 184.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="15.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="30.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="60.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="120.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="240.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="480.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="960.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="1920.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="7680.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:e2e_request_latency_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 651.7642343044281 # HELP vllm:e2e_request_latency_seconds_created Histogram of e2e request latency in seconds. # TYPE vllm:e2e_request_latency_seconds_created gauge vllm:e2e_request_latency_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885349948e+09 # HELP vllm:request_queue_time_seconds Histogram of time spent in WAITING phase for request. # TYPE vllm:request_queue_time_seconds histogram vllm:request_queue_time_seconds_bucket{engine="0",le="0.3",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="0.8",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="1.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="15.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="30.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="60.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="120.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="240.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="480.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="960.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="1920.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="7680.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_queue_time_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 0.0022208726732060313 # HELP vllm:request_queue_time_seconds_created Histogram of time spent in WAITING phase for request. # TYPE vllm:request_queue_time_seconds_created gauge vllm:request_queue_time_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885350182e+09 # HELP vllm:request_inference_time_seconds Histogram of time spent in RUNNING phase for request. # TYPE vllm:request_inference_time_seconds histogram vllm:request_inference_time_seconds_bucket{engine="0",le="0.3",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_inference_time_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_inference_time_seconds_bucket{engine="0",le="0.8",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_inference_time_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_inference_time_seconds_bucket{engine="0",le="1.5",model_name="google/gemma-4-12B-it"} 2.0 vllm:request_inference_time_seconds_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 16.0 vllm:request_inference_time_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 56.0 vllm:request_inference_time_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 184.0 vllm:request_inference_time_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="15.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="30.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="60.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="120.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="240.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="480.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="960.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="1920.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="7680.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_inference_time_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 651.6127791340696 # HELP vllm:request_inference_time_seconds_created Histogram of time spent in RUNNING phase for request. # TYPE vllm:request_inference_time_seconds_created gauge vllm:request_inference_time_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.791241488535042e+09 # HELP vllm:request_prefill_time_seconds Histogram of time spent in PREFILL phase for request. # TYPE vllm:request_prefill_time_seconds histogram vllm:request_prefill_time_seconds_bucket{engine="0",le="0.3",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="0.8",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="1.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="15.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="30.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="60.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="120.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="240.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="480.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="960.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="1920.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="7680.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_time_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 23.952928944141604 # HELP vllm:request_prefill_time_seconds_created Histogram of time spent in PREFILL phase for request. # TYPE vllm:request_prefill_time_seconds_created gauge vllm:request_prefill_time_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885350804e+09 # HELP vllm:request_decode_time_seconds Histogram of time spent in DECODE phase for request. # TYPE vllm:request_decode_time_seconds histogram vllm:request_decode_time_seconds_bucket{engine="0",le="0.3",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_decode_time_seconds_bucket{engine="0",le="0.5",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_decode_time_seconds_bucket{engine="0",le="0.8",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_decode_time_seconds_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_decode_time_seconds_bucket{engine="0",le="1.5",model_name="google/gemma-4-12B-it"} 3.0 vllm:request_decode_time_seconds_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 23.0 vllm:request_decode_time_seconds_bucket{engine="0",le="2.5",model_name="google/gemma-4-12B-it"} 64.0 vllm:request_decode_time_seconds_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 186.0 vllm:request_decode_time_seconds_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="15.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="30.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="40.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="60.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="120.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="240.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="480.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="960.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="1920.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="7680.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_decode_time_seconds_sum{engine="0",model_name="google/gemma-4-12B-it"} 627.659850189928 # HELP vllm:request_decode_time_seconds_created Histogram of time spent in DECODE phase for request. # TYPE vllm:request_decode_time_seconds_created gauge vllm:request_decode_time_seconds_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885351026e+09 # HELP vllm:request_prefill_kv_computed_tokens Histogram of new KV tokens computed during prefill (excluding cached tokens). # TYPE vllm:request_prefill_kv_computed_tokens histogram vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="1.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="10.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="20.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="50.0",model_name="google/gemma-4-12B-it"} 0.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="100.0",model_name="google/gemma-4-12B-it"} 126.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="200.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="500.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="1000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="10000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="20000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="50000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="100000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="200000.0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="+Inf",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_count{engine="0",model_name="google/gemma-4-12B-it"} 200.0 vllm:request_prefill_kv_computed_tokens_sum{engine="0",model_name="google/gemma-4-12B-it"} 19564.0 # HELP vllm:request_prefill_kv_computed_tokens_created Histogram of new KV tokens computed during prefill (excluding cached tokens). # TYPE vllm:request_prefill_kv_computed_tokens_created gauge vllm:request_prefill_kv_computed_tokens_created{engine="0",model_name="google/gemma-4-12B-it"} 1.7912414885351286e+09 # HELP vllm:cache_config_info Information of the LLMEngine CacheConfig # TYPE vllm:cache_config_info gauge vllm:cache_config_info{block_size="64",cache_dtype="auto",calculate_kv_scales="False",cpu_kvcache_space_bytes="None",cpu_offload_gb="0.0",enable_prefix_caching="True",engine="0",gpu_memory_utilization="0.9",is_attention_free="False",kv_cache_memory_bytes="None",kv_offloading_backend="native",kv_offloading_size="None",kv_sharing_fast_prefill="False",mamba_block_size="None",mamba_cache_dtype="auto",mamba_cache_mode="none",mamba_page_size_padded="None",mamba_ssm_cache_dtype="auto",num_cpu_blocks="None",num_gpu_blocks="4097",num_gpu_blocks_override="None",prefix_caching_hash_algo="sha256",sliding_window="None",swap_space="4.0"} 1.0 # HELP http_requests_total Total number of requests by method, status and handler. # TYPE http_requests_total counter http_requests_total{handler="none",method="POST",status="2xx"} 200.0 # HELP http_requests_created Total number of requests by method, status and handler. # TYPE http_requests_created gauge http_requests_created{handler="none",method="POST",status="2xx"} 1.7912414918124118e+09 # HELP http_request_size_bytes Content length of incoming requests by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_request_size_bytes summary http_request_size_bytes_count{handler="none"} 200.0 http_request_size_bytes_sum{handler="none"} 144964.0 # HELP http_request_size_bytes_created Content length of incoming requests by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_request_size_bytes_created gauge http_request_size_bytes_created{handler="none"} 1.7912414918124278e+09 # HELP http_response_size_bytes Content length of outgoing responses by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_response_size_bytes summary http_response_size_bytes_count{handler="none"} 200.0 http_response_size_bytes_sum{handler="none"} 270578.0 # HELP http_response_size_bytes_created Content length of outgoing responses by handler. Only value of header is respected. Otherwise ignored. No percentile calculated. # TYPE http_response_size_bytes_created gauge http_response_size_bytes_created{handler="none"} 1.7912414918124435e+09 # HELP http_request_duration_highr_seconds Latency with many buckets but no API specific labels. Made for more accurate percentile calculations. # TYPE http_request_duration_highr_seconds histogram http_request_duration_highr_seconds_bucket{le="0.01"} 0.0 http_request_duration_highr_seconds_bucket{le="0.025"} 0.0 http_request_duration_highr_seconds_bucket{le="0.05"} 0.0 http_request_duration_highr_seconds_bucket{le="0.075"} 0.0 http_request_duration_highr_seconds_bucket{le="0.1"} 0.0 http_request_duration_highr_seconds_bucket{le="0.25"} 0.0 http_request_duration_highr_seconds_bucket{le="0.5"} 0.0 http_request_duration_highr_seconds_bucket{le="0.75"} 0.0 http_request_duration_highr_seconds_bucket{le="1.0"} 0.0 http_request_duration_highr_seconds_bucket{le="1.5"} 2.0 http_request_duration_highr_seconds_bucket{le="2.0"} 16.0 http_request_duration_highr_seconds_bucket{le="2.5"} 56.0 http_request_duration_highr_seconds_bucket{le="3.0"} 94.0 http_request_duration_highr_seconds_bucket{le="3.5"} 137.0 http_request_duration_highr_seconds_bucket{le="4.0"} 161.0 http_request_duration_highr_seconds_bucket{le="4.5"} 174.0 http_request_duration_highr_seconds_bucket{le="5.0"} 184.0 http_request_duration_highr_seconds_bucket{le="7.5"} 199.0 http_request_duration_highr_seconds_bucket{le="10.0"} 200.0 http_request_duration_highr_seconds_bucket{le="30.0"} 200.0 http_request_duration_highr_seconds_bucket{le="60.0"} 200.0 http_request_duration_highr_seconds_bucket{le="+Inf"} 200.0 http_request_duration_highr_seconds_count 200.0 http_request_duration_highr_seconds_sum 652.0332999337697 # HELP http_request_duration_highr_seconds_created Latency with many buckets but no API specific labels. Made for more accurate percentile calculations. # TYPE http_request_duration_highr_seconds_created gauge http_request_duration_highr_seconds_created 1.791241488619126e+09 # HELP http_request_duration_seconds Latency with only few buckets by handler. Made to be only used if aggregation by handler is important. # TYPE http_request_duration_seconds histogram http_request_duration_seconds_bucket{handler="none",le="0.1",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="none",le="0.5",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="none",le="1.0",method="POST"} 0.0 http_request_duration_seconds_bucket{handler="none",le="+Inf",method="POST"} 200.0 http_request_duration_seconds_count{handler="none",method="POST"} 200.0 http_request_duration_seconds_sum{handler="none",method="POST"} 652.0332999337697 # HELP http_request_duration_seconds_created Latency with only few buckets by handler. Made to be only used if aggregation by handler is important. # TYPE http_request_duration_seconds_created gauge http_request_duration_seconds_created{handler="none",method="POST"} 1.7912414918124666e+09