# HELP python_gc_objects_collected_total Objects collected during gc
# TYPE python_gc_objects_collected_total counter
python_gc_objects_collected_total{generation="0"} 14178.0
python_gc_objects_collected_total{generation="1"} 2556.0
python_gc_objects_collected_total{generation="2"} 582.0
# 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"} 9333.0
python_gc_collections_total{generation="1"} 848.0
python_gc_collections_total{generation="2"} 70.0
# HELP python_info Python platform information
# TYPE python_info gauge
python_info{implementation="CPython",major="3",minor="12",patchlevel="3",version="3.12.3"} 1.0
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 9.791025152e+09
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 1.799634944e+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 1.78081350347e+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 2326.1200000000003
# HELP process_open_fds Number of open file descriptors.
# TYPE process_open_fds gauge
process_open_fds 38.0
# 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="qwen3-30b-tq"} 2.121962e+06
# 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="qwen3-30b-tq"} 1.7808138561820862e+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="qwen3-30b-tq"} 1.1501084e+07
# 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="qwen3-30b-tq"} 1.7808138561821108e+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="qwen3-30b-tq"} 4.574989e+06
# 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="qwen3-30b-tq"} 1.7808138561821258e+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="qwen3-30b-tq",position="0"} 1.142461e+06
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3-30b-tq",position="1"} 813147.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3-30b-tq",position="2"} 570926.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3-30b-tq",position="3"} 501633.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3-30b-tq",position="4"} 433208.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3-30b-tq",position="5"} 410782.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3-30b-tq",position="6"} 372466.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3-30b-tq",position="7"} 330366.0
# 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="qwen3-30b-tq",position="0"} 1.780813856182158e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3-30b-tq",position="1"} 1.7808138561821651e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3-30b-tq",position="2"} 1.7808138561821747e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3-30b-tq",position="3"} 1.7808138561821806e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3-30b-tq",position="4"} 1.780813856182186e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3-30b-tq",position="5"} 1.780813856182191e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3-30b-tq",position="6"} 1.7808138561821954e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3-30b-tq",position="7"} 1.7808138561822e+09
# HELP vllm:estimated_flops_per_gpu_total Estimated number of floating point operations per GPU (for Model Flops Utilization calculations).
# TYPE vllm:estimated_flops_per_gpu_total counter
vllm:estimated_flops_per_gpu_total{engine="0",model_name="qwen3-30b-tq"} 0.0
# HELP vllm:estimated_flops_per_gpu_created Estimated number of floating point operations per GPU (for Model Flops Utilization calculations).
# TYPE vllm:estimated_flops_per_gpu_created gauge
vllm:estimated_flops_per_gpu_created{engine="0",model_name="qwen3-30b-tq"} 1.780813856182232e+09
# HELP vllm:estimated_read_bytes_per_gpu_total Estimated number of bytes read from memory per GPU (for Model Flops Utilization calculations).
# TYPE vllm:estimated_read_bytes_per_gpu_total counter
vllm:estimated_read_bytes_per_gpu_total{engine="0",model_name="qwen3-30b-tq"} 0.0
# HELP vllm:estimated_read_bytes_per_gpu_created Estimated number of bytes read from memory per GPU (for Model Flops Utilization calculations).
# TYPE vllm:estimated_read_bytes_per_gpu_created gauge
vllm:estimated_read_bytes_per_gpu_created{engine="0",model_name="qwen3-30b-tq"} 1.7808138561822464e+09
# HELP vllm:estimated_write_bytes_per_gpu_total Estimated number of bytes written to memory per GPU (for Model Flops Utilization calculations).
# TYPE vllm:estimated_write_bytes_per_gpu_total counter
vllm:estimated_write_bytes_per_gpu_total{engine="0",model_name="qwen3-30b-tq"} 0.0
# HELP vllm:estimated_write_bytes_per_gpu_created Estimated number of bytes written to memory per GPU (for Model Flops Utilization calculations).
# TYPE vllm:estimated_write_bytes_per_gpu_created gauge
vllm:estimated_write_bytes_per_gpu_created{engine="0",model_name="qwen3-30b-tq"} 1.7808138561822636e+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="qwen3-30b-tq"} 1.0
# 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="qwen3-30b-tq"} 2.0
# 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="qwen3-30b-tq",sleep_state="awake"} 1.0
vllm:engine_sleep_state{engine="0",model_name="qwen3-30b-tq",sleep_state="weights_offloaded"} 0.0
vllm:engine_sleep_state{engine="0",model_name="qwen3-30b-tq",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="qwen3-30b-tq"} 0.0010077742585661298
# 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="qwen3-30b-tq"} 1.9106864e+07
# 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="qwen3-30b-tq"} 1.7808138561824472e+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="qwen3-30b-tq"} 5.819712e+06
# 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="qwen3-30b-tq"} 1.7808138561824684e+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="qwen3-30b-tq"} 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="qwen3-30b-tq"} 1.78081385618248e+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="qwen3-30b-tq"} 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="qwen3-30b-tq"} 1.7808138561824913e+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="qwen3-30b-tq"} 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="qwen3-30b-tq"} 1.7808138561825068e+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="qwen3-30b-tq"} 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="qwen3-30b-tq"} 1.7808138561825175e+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="qwen3-30b-tq"} 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="qwen3-30b-tq"} 1.7808138561825285e+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="qwen3-30b-tq"} 1.9045253e+07
# HELP vllm:prompt_tokens_created Number of prefill tokens processed.
# TYPE vllm:prompt_tokens_created gauge
vllm:prompt_tokens_created{engine="0",model_name="qwen3-30b-tq"} 1.7808138561825402e+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="qwen3-30b-tq",source="local_compute"} 1.3252037e+07
vllm:prompt_tokens_by_source_total{engine="0",model_name="qwen3-30b-tq",source="local_cache_hit"} 5.793904e+06
vllm:prompt_tokens_by_source_total{engine="0",model_name="qwen3-30b-tq",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="qwen3-30b-tq",source="local_compute"} 1.7808138561825655e+09
vllm:prompt_tokens_by_source_created{engine="0",model_name="qwen3-30b-tq",source="local_cache_hit"} 1.78081385618258e+09
vllm:prompt_tokens_by_source_created{engine="0",model_name="qwen3-30b-tq",source="external_kv_transfer"} 1.7808138561825857e+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="qwen3-30b-tq"} 5.793216e+06
# 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="qwen3-30b-tq"} 1.7808138561825979e+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="qwen3-30b-tq"} 688.0
# 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="qwen3-30b-tq"} 1.78081385618261e+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="qwen3-30b-tq"} 6.723875e+06
# HELP vllm:generation_tokens_created Number of generation tokens processed.
# TYPE vllm:generation_tokens_created gauge
vllm:generation_tokens_created{engine="0",model_name="qwen3-30b-tq"} 1.7808138561828825e+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="qwen3-30b-tq"} 51319.0
vllm:request_success_total{engine="0",finished_reason="length",model_name="qwen3-30b-tq"} 724.0
vllm:request_success_total{engine="0",finished_reason="abort",model_name="qwen3-30b-tq"} 0.0
vllm:request_success_total{engine="0",finished_reason="error",model_name="qwen3-30b-tq"} 0.0
vllm:request_success_total{engine="0",finished_reason="repetition",model_name="qwen3-30b-tq"} 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="qwen3-30b-tq"} 1.780813856182919e+09
vllm:request_success_created{engine="0",finished_reason="length",model_name="qwen3-30b-tq"} 1.7808138561829271e+09
vllm:request_success_created{engine="0",finished_reason="abort",model_name="qwen3-30b-tq"} 1.7808138561829336e+09
vllm:request_success_created{engine="0",finished_reason="error",model_name="qwen3-30b-tq"} 1.7808138561829386e+09
vllm:request_success_created{engine="0",finished_reason="repetition",model_name="qwen3-30b-tq"} 1.7808138561829486e+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="qwen3-30b-tq"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 8.0
vllm:request_prompt_tokens_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_prompt_tokens_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 10.0
vllm:request_prompt_tokens_bucket{engine="0",le="100.0",model_name="qwen3-30b-tq"} 10.0
vllm:request_prompt_tokens_bucket{engine="0",le="200.0",model_name="qwen3-30b-tq"} 10.0
vllm:request_prompt_tokens_bucket{engine="0",le="500.0",model_name="qwen3-30b-tq"} 49264.0
vllm:request_prompt_tokens_bucket{engine="0",le="1000.0",model_name="qwen3-30b-tq"} 51944.0
vllm:request_prompt_tokens_bucket{engine="0",le="2000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_bucket{engine="0",le="5000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_bucket{engine="0",le="10000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_bucket{engine="0",le="20000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_bucket{engine="0",le="50000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_bucket{engine="0",le="100000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_bucket{engine="0",le="200000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prompt_tokens_sum{engine="0",model_name="qwen3-30b-tq"} 1.8754362e+07
# 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="qwen3-30b-tq"} 1.7808138561830242e+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="qwen3-30b-tq"} 7.0
vllm:request_generation_tokens_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_generation_tokens_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_generation_tokens_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_generation_tokens_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_generation_tokens_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 15.0
vllm:request_generation_tokens_bucket{engine="0",le="100.0",model_name="qwen3-30b-tq"} 16553.0
vllm:request_generation_tokens_bucket{engine="0",le="200.0",model_name="qwen3-30b-tq"} 49045.0
vllm:request_generation_tokens_bucket{engine="0",le="500.0",model_name="qwen3-30b-tq"} 51317.0
vllm:request_generation_tokens_bucket{engine="0",le="1000.0",model_name="qwen3-30b-tq"} 51339.0
vllm:request_generation_tokens_bucket{engine="0",le="2000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_bucket{engine="0",le="5000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_bucket{engine="0",le="10000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_bucket{engine="0",le="20000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_bucket{engine="0",le="50000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_bucket{engine="0",le="100000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_bucket{engine="0",le="200000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_generation_tokens_sum{engine="0",model_name="qwen3-30b-tq"} 6.636226e+06
# 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="qwen3-30b-tq"} 1.7808138561831074e+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="qwen3-30b-tq"} 1.013749e+06
vllm:iteration_tokens_total_bucket{engine="0",le="8.0",model_name="qwen3-30b-tq"} 1.826346e+06
vllm:iteration_tokens_total_bucket{engine="0",le="16.0",model_name="qwen3-30b-tq"} 2.155469e+06
vllm:iteration_tokens_total_bucket{engine="0",le="32.0",model_name="qwen3-30b-tq"} 2.155469e+06
vllm:iteration_tokens_total_bucket{engine="0",le="64.0",model_name="qwen3-30b-tq"} 2.15547e+06
vllm:iteration_tokens_total_bucket{engine="0",le="128.0",model_name="qwen3-30b-tq"} 2.15547e+06
vllm:iteration_tokens_total_bucket{engine="0",le="256.0",model_name="qwen3-30b-tq"} 2.15547e+06
vllm:iteration_tokens_total_bucket{engine="0",le="512.0",model_name="qwen3-30b-tq"} 2.205574e+06
vllm:iteration_tokens_total_bucket{engine="0",le="1024.0",model_name="qwen3-30b-tq"} 2.208275e+06
vllm:iteration_tokens_total_bucket{engine="0",le="2048.0",model_name="qwen3-30b-tq"} 2.208376e+06
vllm:iteration_tokens_total_bucket{engine="0",le="4096.0",model_name="qwen3-30b-tq"} 2.208376e+06
vllm:iteration_tokens_total_bucket{engine="0",le="8192.0",model_name="qwen3-30b-tq"} 2.208376e+06
vllm:iteration_tokens_total_bucket{engine="0",le="16384.0",model_name="qwen3-30b-tq"} 2.208376e+06
vllm:iteration_tokens_total_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 2.208376e+06
vllm:iteration_tokens_total_count{engine="0",model_name="qwen3-30b-tq"} 2.208376e+06
vllm:iteration_tokens_total_sum{engine="0",model_name="qwen3-30b-tq"} 2.5769128e+07
# 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="qwen3-30b-tq"} 1.780813856183155e+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="qwen3-30b-tq"} 7.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 15.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="100.0",model_name="qwen3-30b-tq"} 16553.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="200.0",model_name="qwen3-30b-tq"} 49045.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="500.0",model_name="qwen3-30b-tq"} 51317.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="1000.0",model_name="qwen3-30b-tq"} 51339.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="2000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="5000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="10000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="20000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="50000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="100000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="200000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_max_num_generation_tokens_sum{engine="0",model_name="qwen3-30b-tq"} 6.636226e+06
# 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="qwen3-30b-tq"} 1.7808138561832225e+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="qwen3-30b-tq"} 52043.0
vllm:request_params_n_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_n_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_n_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_n_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_n_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_n_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_n_sum{engine="0",model_name="qwen3-30b-tq"} 52043.0
# 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="qwen3-30b-tq"} 1.7808138561832976e+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="qwen3-30b-tq"} 7.0
vllm:request_params_max_tokens_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 7.0
vllm:request_params_max_tokens_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 8.0
vllm:request_params_max_tokens_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_params_max_tokens_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_params_max_tokens_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_params_max_tokens_bucket{engine="0",le="100.0",model_name="qwen3-30b-tq"} 9.0
vllm:request_params_max_tokens_bucket{engine="0",le="200.0",model_name="qwen3-30b-tq"} 10.0
vllm:request_params_max_tokens_bucket{engine="0",le="500.0",model_name="qwen3-30b-tq"} 10.0
vllm:request_params_max_tokens_bucket{engine="0",le="1000.0",model_name="qwen3-30b-tq"} 2661.0
vllm:request_params_max_tokens_bucket{engine="0",le="2000.0",model_name="qwen3-30b-tq"} 52041.0
vllm:request_params_max_tokens_bucket{engine="0",le="5000.0",model_name="qwen3-30b-tq"} 52041.0
vllm:request_params_max_tokens_bucket{engine="0",le="10000.0",model_name="qwen3-30b-tq"} 52041.0
vllm:request_params_max_tokens_bucket{engine="0",le="20000.0",model_name="qwen3-30b-tq"} 52041.0
vllm:request_params_max_tokens_bucket{engine="0",le="50000.0",model_name="qwen3-30b-tq"} 52041.0
vllm:request_params_max_tokens_bucket{engine="0",le="100000.0",model_name="qwen3-30b-tq"} 52041.0
vllm:request_params_max_tokens_bucket{engine="0",le="200000.0",model_name="qwen3-30b-tq"} 52041.0
vllm:request_params_max_tokens_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_max_tokens_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_params_max_tokens_sum{engine="0",model_name="qwen3-30b-tq"} 5.2678957e+07
# 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="qwen3-30b-tq"} 1.780813856183345e+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="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.005",model_name="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.01",model_name="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.02",model_name="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.04",model_name="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.06",model_name="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.08",model_name="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.1",model_name="qwen3-30b-tq"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.25",model_name="qwen3-30b-tq"} 439.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 9216.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.75",model_name="qwen3-30b-tq"} 9276.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 9323.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 9453.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 10234.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="7.5",model_name="qwen3-30b-tq"} 12613.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 14159.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 22231.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 33588.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="80.0",model_name="qwen3-30b-tq"} 38151.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="160.0",model_name="qwen3-30b-tq"} 42467.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="640.0",model_name="qwen3-30b-tq"} 52916.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="2560.0",model_name="qwen3-30b-tq"} 52916.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52916.0
vllm:time_to_first_token_seconds_count{engine="0",model_name="qwen3-30b-tq"} 52916.0
vllm:time_to_first_token_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 3.8408829580595493e+06
# 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="qwen3-30b-tq"} 1.7808138561833892e+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="qwen3-30b-tq"} 0.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.025",model_name="qwen3-30b-tq"} 0.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.05",model_name="qwen3-30b-tq"} 0.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.075",model_name="qwen3-30b-tq"} 0.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.1",model_name="qwen3-30b-tq"} 1931.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.15",model_name="qwen3-30b-tq"} 68751.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.2",model_name="qwen3-30b-tq"} 2.004736e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.3",model_name="qwen3-30b-tq"} 2.153678e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.4",model_name="qwen3-30b-tq"} 2.155357e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 2.155426e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.75",model_name="qwen3-30b-tq"} 2.155452e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 2.155455e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 2.155456e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 2.155456e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="7.5",model_name="qwen3-30b-tq"} 2.155456e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 2.155456e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 2.155457e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 2.155457e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="80.0",model_name="qwen3-30b-tq"} 2.155457e+06
vllm:inter_token_latency_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 2.155457e+06
vllm:inter_token_latency_seconds_count{engine="0",model_name="qwen3-30b-tq"} 2.155457e+06
vllm:inter_token_latency_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 366813.3155220201
# 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="qwen3-30b-tq"} 1.7808138561834357e+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="qwen3-30b-tq"} 7.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.025",model_name="qwen3-30b-tq"} 709.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.05",model_name="qwen3-30b-tq"} 15041.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.075",model_name="qwen3-30b-tq"} 47947.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.1",model_name="qwen3-30b-tq"} 51836.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.15",model_name="qwen3-30b-tq"} 52041.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.2",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.3",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.4",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.75",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="7.5",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 52042.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="80.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_time_per_output_token_seconds_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_time_per_output_token_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 2979.432286309289
# 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="qwen3-30b-tq"} 1.780813856183475e+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="qwen3-30b-tq"} 6.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 7.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.8",model_name="qwen3-30b-tq"} 7.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 7.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.5",model_name="qwen3-30b-tq"} 8.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 9.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 15.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 1357.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 8125.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="15.0",model_name="qwen3-30b-tq"} 11804.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 15052.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="30.0",model_name="qwen3-30b-tq"} 25947.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 31346.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 34183.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="60.0",model_name="qwen3-30b-tq"} 35747.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="120.0",model_name="qwen3-30b-tq"} 40132.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="240.0",model_name="qwen3-30b-tq"} 45804.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="480.0",model_name="qwen3-30b-tq"} 52043.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="960.0",model_name="qwen3-30b-tq"} 52043.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1920.0",model_name="qwen3-30b-tq"} 52043.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="7680.0",model_name="qwen3-30b-tq"} 52043.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:e2e_request_latency_seconds_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:e2e_request_latency_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 3.9461616393609047e+06
# 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="qwen3-30b-tq"} 1.780813856183513e+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="qwen3-30b-tq"} 9313.0
vllm:request_queue_time_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 9321.0
vllm:request_queue_time_seconds_bucket{engine="0",le="0.8",model_name="qwen3-30b-tq"} 9349.0
vllm:request_queue_time_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 9369.0
vllm:request_queue_time_seconds_bucket{engine="0",le="1.5",model_name="qwen3-30b-tq"} 9409.0
vllm:request_queue_time_seconds_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 9448.0
vllm:request_queue_time_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 9495.0
vllm:request_queue_time_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 10643.0
vllm:request_queue_time_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 14387.0
vllm:request_queue_time_seconds_bucket{engine="0",le="15.0",model_name="qwen3-30b-tq"} 17295.0
vllm:request_queue_time_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 23001.0
vllm:request_queue_time_seconds_bucket{engine="0",le="30.0",model_name="qwen3-30b-tq"} 30782.0
vllm:request_queue_time_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 33681.0
vllm:request_queue_time_seconds_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 35487.0
vllm:request_queue_time_seconds_bucket{engine="0",le="60.0",model_name="qwen3-30b-tq"} 36691.0
vllm:request_queue_time_seconds_bucket{engine="0",le="120.0",model_name="qwen3-30b-tq"} 40469.0
vllm:request_queue_time_seconds_bucket{engine="0",le="240.0",model_name="qwen3-30b-tq"} 46120.0
vllm:request_queue_time_seconds_bucket{engine="0",le="480.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_queue_time_seconds_bucket{engine="0",le="960.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_queue_time_seconds_bucket{engine="0",le="1920.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_queue_time_seconds_bucket{engine="0",le="7680.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_queue_time_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_queue_time_seconds_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_queue_time_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 3.560128002164351e+06
# 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="qwen3-30b-tq"} 1.7808138561835546e+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="qwen3-30b-tq"} 7.0
vllm:request_inference_time_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 8.0
vllm:request_inference_time_seconds_bucket{engine="0",le="0.8",model_name="qwen3-30b-tq"} 8.0
vllm:request_inference_time_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 8.0
vllm:request_inference_time_seconds_bucket{engine="0",le="1.5",model_name="qwen3-30b-tq"} 9.0
vllm:request_inference_time_seconds_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 26.0
vllm:request_inference_time_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 178.0
vllm:request_inference_time_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 11491.0
vllm:request_inference_time_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 47063.0
vllm:request_inference_time_seconds_bucket{engine="0",le="15.0",model_name="qwen3-30b-tq"} 49216.0
vllm:request_inference_time_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 50062.0
vllm:request_inference_time_seconds_bucket{engine="0",le="30.0",model_name="qwen3-30b-tq"} 51759.0
vllm:request_inference_time_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 52022.0
vllm:request_inference_time_seconds_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 52039.0
vllm:request_inference_time_seconds_bucket{engine="0",le="60.0",model_name="qwen3-30b-tq"} 52042.0
vllm:request_inference_time_seconds_bucket{engine="0",le="120.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_bucket{engine="0",le="240.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_bucket{engine="0",le="480.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_bucket{engine="0",le="960.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_bucket{engine="0",le="1920.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_bucket{engine="0",le="7680.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_inference_time_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 378509.94189713517
# 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="qwen3-30b-tq"} 1.7808138561835983e+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="qwen3-30b-tq"} 25530.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 51910.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.8",model_name="qwen3-30b-tq"} 51989.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 52029.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.5",model_name="qwen3-30b-tq"} 52039.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 52040.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 52040.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 52040.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="15.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="30.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="60.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="120.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="240.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="480.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="960.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="1920.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="7680.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_time_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 14951.528692015272
# 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="qwen3-30b-tq"} 1.7808138561836348e+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="qwen3-30b-tq"} 8.0
vllm:request_decode_time_seconds_bucket{engine="0",le="0.5",model_name="qwen3-30b-tq"} 8.0
vllm:request_decode_time_seconds_bucket{engine="0",le="0.8",model_name="qwen3-30b-tq"} 8.0
vllm:request_decode_time_seconds_bucket{engine="0",le="1.0",model_name="qwen3-30b-tq"} 8.0
vllm:request_decode_time_seconds_bucket{engine="0",le="1.5",model_name="qwen3-30b-tq"} 10.0
vllm:request_decode_time_seconds_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 58.0
vllm:request_decode_time_seconds_bucket{engine="0",le="2.5",model_name="qwen3-30b-tq"} 369.0
vllm:request_decode_time_seconds_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 14164.0
vllm:request_decode_time_seconds_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 47448.0
vllm:request_decode_time_seconds_bucket{engine="0",le="15.0",model_name="qwen3-30b-tq"} 49276.0
vllm:request_decode_time_seconds_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 50131.0
vllm:request_decode_time_seconds_bucket{engine="0",le="30.0",model_name="qwen3-30b-tq"} 51788.0
vllm:request_decode_time_seconds_bucket{engine="0",le="40.0",model_name="qwen3-30b-tq"} 52024.0
vllm:request_decode_time_seconds_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 52039.0
vllm:request_decode_time_seconds_bucket{engine="0",le="60.0",model_name="qwen3-30b-tq"} 52042.0
vllm:request_decode_time_seconds_bucket{engine="0",le="120.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_bucket{engine="0",le="240.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_bucket{engine="0",le="480.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_bucket{engine="0",le="960.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_bucket{engine="0",le="1920.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_bucket{engine="0",le="7680.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_decode_time_seconds_sum{engine="0",model_name="qwen3-30b-tq"} 363558.4132051199
# 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="qwen3-30b-tq"} 1.7808138561836777e+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="qwen3-30b-tq"} 660.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2.0",model_name="qwen3-30b-tq"} 1293.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5.0",model_name="qwen3-30b-tq"} 2534.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="10.0",model_name="qwen3-30b-tq"} 3415.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="20.0",model_name="qwen3-30b-tq"} 4182.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="50.0",model_name="qwen3-30b-tq"} 4834.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="100.0",model_name="qwen3-30b-tq"} 13481.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="200.0",model_name="qwen3-30b-tq"} 13481.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="500.0",model_name="qwen3-30b-tq"} 49963.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="1000.0",model_name="qwen3-30b-tq"} 51953.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="10000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="20000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="50000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="100000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="200000.0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="+Inf",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_count{engine="0",model_name="qwen3-30b-tq"} 52043.0
vllm:request_prefill_kv_computed_tokens_sum{engine="0",model_name="qwen3-30b-tq"} 1.3101178e+07
# 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="qwen3-30b-tq"} 1.7808138561837575e+09
# HELP vllm:cache_config_info Information of the LLMEngine CacheConfig
# TYPE vllm:cache_config_info gauge
vllm:cache_config_info{_block_size_resolved="True",block_size="64",cache_dtype="turboquant_k3v4_nc",calculate_kv_scales="False",cpu_kvcache_space_bytes="None",enable_prefix_caching="True",engine="0",gpu_memory_utilization="0.9",is_attention_free="False",kv_cache_dtype_skip_layers="[]",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="6947",num_gpu_blocks_override="None",prefix_caching_hash_algo="sha256",sliding_window="None",user_specified_block_size="False"} 1.0
# HELP http_requests_total Total number of requests by method, status and handler.
# TYPE http_requests_total counter
http_requests_total{handler="/v1/chat/completions",method="POST",status="2xx"} 56090.0
http_requests_total{handler="/v1/chat/completions",method="POST",status="4xx"} 7.0
http_requests_total{handler="/v1/models",method="GET",status="2xx"} 3.0
# HELP http_requests_created Total number of requests by method, status and handler.
# TYPE http_requests_created gauge
http_requests_created{handler="/v1/chat/completions",method="POST",status="2xx"} 1.7808138794839e+09
http_requests_created{handler="/v1/chat/completions",method="POST",status="4xx"} 1.7808984021500945e+09
http_requests_created{handler="/v1/models",method="GET",status="2xx"} 1.7810651828606594e+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="/v1/chat/completions"} 56097.0
http_request_size_bytes_sum{handler="/v1/chat/completions"} 9.1221765e+07
http_request_size_bytes_count{handler="/v1/models"} 3.0
http_request_size_bytes_sum{handler="/v1/models"} 0.0
# 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="/v1/chat/completions"} 1.78081387948393e+09
http_request_size_bytes_created{handler="/v1/models"} 1.7810651828607123e+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="/v1/chat/completions"} 56097.0
http_response_size_bytes_sum{handler="/v1/chat/completions"} 5.5888696e+07
http_response_size_bytes_count{handler="/v1/models"} 3.0
http_response_size_bytes_sum{handler="/v1/models"} 1509.0
# 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="/v1/chat/completions"} 1.7808138794839733e+09
http_response_size_bytes_created{handler="/v1/models"} 1.7810651828607335e+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"} 10.0
http_request_duration_highr_seconds_bucket{le="0.025"} 10.0
http_request_duration_highr_seconds_bucket{le="0.05"} 10.0
http_request_duration_highr_seconds_bucket{le="0.075"} 10.0
http_request_duration_highr_seconds_bucket{le="0.1"} 10.0
http_request_duration_highr_seconds_bucket{le="0.25"} 16.0
http_request_duration_highr_seconds_bucket{le="0.5"} 17.0
http_request_duration_highr_seconds_bucket{le="0.75"} 17.0
http_request_duration_highr_seconds_bucket{le="1.0"} 17.0
http_request_duration_highr_seconds_bucket{le="1.5"} 18.0
http_request_duration_highr_seconds_bucket{le="2.0"} 19.0
http_request_duration_highr_seconds_bucket{le="2.5"} 25.0
http_request_duration_highr_seconds_bucket{le="3.0"} 51.0
http_request_duration_highr_seconds_bucket{le="3.5"} 164.0
http_request_duration_highr_seconds_bucket{le="4.0"} 387.0
http_request_duration_highr_seconds_bucket{le="4.5"} 789.0
http_request_duration_highr_seconds_bucket{le="5.0"} 1362.0
http_request_duration_highr_seconds_bucket{le="7.5"} 5773.0
http_request_duration_highr_seconds_bucket{le="10.0"} 8135.0
http_request_duration_highr_seconds_bucket{le="30.0"} 25959.0
http_request_duration_highr_seconds_bucket{le="60.0"} 35759.0
http_request_duration_highr_seconds_bucket{le="+Inf"} 56100.0
http_request_duration_highr_seconds_count 56100.0
http_request_duration_highr_seconds_sum 5.159986640046089e+06
# 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 1.780813856528641e+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="/v1/chat/completions",le="0.1",method="POST"} 7.0
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="0.5",method="POST"} 14.0
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="1.0",method="POST"} 14.0
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="+Inf",method="POST"} 56097.0
http_request_duration_seconds_count{handler="/v1/chat/completions",method="POST"} 56097.0
http_request_duration_seconds_sum{handler="/v1/chat/completions",method="POST"} 5.1599866365231415e+06
http_request_duration_seconds_bucket{handler="/v1/models",le="0.1",method="GET"} 3.0
http_request_duration_seconds_bucket{handler="/v1/models",le="0.5",method="GET"} 3.0
http_request_duration_seconds_bucket{handler="/v1/models",le="1.0",method="GET"} 3.0
http_request_duration_seconds_bucket{handler="/v1/models",le="+Inf",method="GET"} 3.0
http_request_duration_seconds_count{handler="/v1/models",method="GET"} 3.0
http_request_duration_seconds_sum{handler="/v1/models",method="GET"} 0.003522945218719542
# 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="/v1/chat/completions",method="POST"} 1.7808138794840076e+09
http_request_duration_seconds_created{handler="/v1/models",method="GET"} 1.7810651828608289e+09
