# HELP python_gc_objects_collected_total Objects collected during gc
# TYPE python_gc_objects_collected_total counter
python_gc_objects_collected_total{generation="0"} 17549.0
python_gc_objects_collected_total{generation="1"} 2875.0
python_gc_objects_collected_total{generation="2"} 523.0
# 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"} 2134.0
python_gc_collections_total{generation="1"} 194.0
python_gc_collections_total{generation="2"} 10.0
# 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 7.183286272e+09
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 5.343367168e+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 1.7907796865e+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 41.87
# HELP process_open_fds Number of open file descriptors.
# TYPE process_open_fds gauge
process_open_fds 42.0
# HELP process_max_fds Maximum number of open file descriptors.
# TYPE process_max_fds gauge
process_max_fds 1.048576e+06
# 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="tensward-t8-ngram-speculation-screen"} 492.0
# 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="tensward-t8-ngram-speculation-screen"} 1.790780013392864e+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="tensward-t8-ngram-speculation-screen"} 1968.0
# 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="tensward-t8-ngram-speculation-screen"} 1.790780013392899e+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="tensward-t8-ngram-speculation-screen"} 950.0
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133929229e+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="tensward-t8-ngram-speculation-screen",position="0"} 328.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="tensward-t8-ngram-speculation-screen",position="1"} 241.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="tensward-t8-ngram-speculation-screen",position="2"} 205.0
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="tensward-t8-ngram-speculation-screen",position="3"} 176.0
# 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="tensward-t8-ngram-speculation-screen",position="0"} 1.7907800133929522e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="tensward-t8-ngram-speculation-screen",position="1"} 1.7907800133929615e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="tensward-t8-ngram-speculation-screen",position="2"} 1.79078001339297e+09
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="tensward-t8-ngram-speculation-screen",position="3"} 1.790780013392978e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133930097e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.790780013393038e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133930573e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 0.0
# HELP vllm:num_requests_waiting_by_reason Number of waiting requests by reason. Reason labels: 'capacity' = waiting for scheduling capacity; 'deferred' = deferred by transient constraints (LoRA budget, KV transfer, blocked status). Sum of all reasons equals vllm:num_requests_waiting.
# TYPE vllm:num_requests_waiting_by_reason gauge
vllm:num_requests_waiting_by_reason{engine="0",model_name="tensward-t8-ngram-speculation-screen",reason="capacity"} 0.0
vllm:num_requests_waiting_by_reason{engine="0",model_name="tensward-t8-ngram-speculation-screen",reason="deferred"} 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="tensward-t8-ngram-speculation-screen",sleep_state="awake"} 1.0
vllm:engine_sleep_state{engine="0",model_name="tensward-t8-ngram-speculation-screen",sleep_state="weights_offloaded"} 0.0
vllm:engine_sleep_state{engine="0",model_name="tensward-t8-ngram-speculation-screen",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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 0.0
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133933372e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133933635e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133933873e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133934052e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133934329e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133934653e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133934848e+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="tensward-t8-ngram-speculation-screen"} 51187.0
# HELP vllm:prompt_tokens_created Number of prefill tokens processed.
# TYPE vllm:prompt_tokens_created gauge
vllm:prompt_tokens_created{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 1.790780013393504e+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="tensward-t8-ngram-speculation-screen",source="local_compute"} 51187.0
vllm:prompt_tokens_by_source_total{engine="0",model_name="tensward-t8-ngram-speculation-screen",source="local_cache_hit"} 0.0
vllm:prompt_tokens_by_source_total{engine="0",model_name="tensward-t8-ngram-speculation-screen",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="tensward-t8-ngram-speculation-screen",source="local_compute"} 1.7907800133935266e+09
vllm:prompt_tokens_by_source_created{engine="0",model_name="tensward-t8-ngram-speculation-screen",source="local_cache_hit"} 1.7907800133935413e+09
vllm:prompt_tokens_by_source_created{engine="0",model_name="tensward-t8-ngram-speculation-screen",source="external_kv_transfer"} 1.79078001339355e+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="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.790780013393568e+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="tensward-t8-ngram-speculation-screen"} 4713.0
# HELP vllm:generation_tokens_created Number of generation tokens processed.
# TYPE vllm:generation_tokens_created gauge
vllm:generation_tokens_created{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 1.7907800133935952e+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="tensward-t8-ngram-speculation-screen"} 32.0
vllm:request_success_total{engine="0",finished_reason="length",model_name="tensward-t8-ngram-speculation-screen"} 20.0
vllm:request_success_total{engine="0",finished_reason="abort",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_success_total{engine="0",finished_reason="error",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_success_total{engine="0",finished_reason="repetition",model_name="tensward-t8-ngram-speculation-screen"} 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="tensward-t8-ngram-speculation-screen"} 1.7907800133936288e+09
vllm:request_success_created{engine="0",finished_reason="length",model_name="tensward-t8-ngram-speculation-screen"} 1.7907800133936443e+09
vllm:request_success_created{engine="0",finished_reason="abort",model_name="tensward-t8-ngram-speculation-screen"} 1.7907800133937938e+09
vllm:request_success_created{engine="0",finished_reason="error",model_name="tensward-t8-ngram-speculation-screen"} 1.7907800133938053e+09
vllm:request_success_created{engine="0",finished_reason="repetition",model_name="tensward-t8-ngram-speculation-screen"} 1.790780013393815e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="100.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prompt_tokens_bucket{engine="0",le="200.0",model_name="tensward-t8-ngram-speculation-screen"} 1.0
vllm:request_prompt_tokens_bucket{engine="0",le="500.0",model_name="tensward-t8-ngram-speculation-screen"} 10.0
vllm:request_prompt_tokens_bucket{engine="0",le="1000.0",model_name="tensward-t8-ngram-speculation-screen"} 41.0
vllm:request_prompt_tokens_bucket{engine="0",le="2000.0",model_name="tensward-t8-ngram-speculation-screen"} 47.0
vllm:request_prompt_tokens_bucket{engine="0",le="5000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prompt_tokens_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prompt_tokens_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prompt_tokens_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 51187.0
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133938825e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_generation_tokens_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_generation_tokens_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 2.0
vllm:request_generation_tokens_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 6.0
vllm:request_generation_tokens_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 8.0
vllm:request_generation_tokens_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 14.0
vllm:request_generation_tokens_bucket{engine="0",le="100.0",model_name="tensward-t8-ngram-speculation-screen"} 25.0
vllm:request_generation_tokens_bucket{engine="0",le="200.0",model_name="tensward-t8-ngram-speculation-screen"} 51.0
vllm:request_generation_tokens_bucket{engine="0",le="500.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_generation_tokens_bucket{engine="0",le="1000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_generation_tokens_bucket{engine="0",le="2000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_generation_tokens_bucket{engine="0",le="5000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_generation_tokens_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_generation_tokens_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_generation_tokens_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 4713.0
# 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="tensward-t8-ngram-speculation-screen"} 1.790780013393962e+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="tensward-t8-ngram-speculation-screen"} 41.0
vllm:iteration_tokens_total_bucket{engine="0",le="8.0",model_name="tensward-t8-ngram-speculation-screen"} 181.0
vllm:iteration_tokens_total_bucket{engine="0",le="16.0",model_name="tensward-t8-ngram-speculation-screen"} 197.0
vllm:iteration_tokens_total_bucket{engine="0",le="32.0",model_name="tensward-t8-ngram-speculation-screen"} 245.0
vllm:iteration_tokens_total_bucket{engine="0",le="64.0",model_name="tensward-t8-ngram-speculation-screen"} 293.0
vllm:iteration_tokens_total_bucket{engine="0",le="128.0",model_name="tensward-t8-ngram-speculation-screen"} 293.0
vllm:iteration_tokens_total_bucket{engine="0",le="256.0",model_name="tensward-t8-ngram-speculation-screen"} 293.0
vllm:iteration_tokens_total_bucket{engine="0",le="512.0",model_name="tensward-t8-ngram-speculation-screen"} 294.0
vllm:iteration_tokens_total_bucket{engine="0",le="1024.0",model_name="tensward-t8-ngram-speculation-screen"} 302.0
vllm:iteration_tokens_total_bucket{engine="0",le="2048.0",model_name="tensward-t8-ngram-speculation-screen"} 313.0
vllm:iteration_tokens_total_bucket{engine="0",le="4096.0",model_name="tensward-t8-ngram-speculation-screen"} 322.0
vllm:iteration_tokens_total_bucket{engine="0",le="8192.0",model_name="tensward-t8-ngram-speculation-screen"} 322.0
vllm:iteration_tokens_total_bucket{engine="0",le="16384.0",model_name="tensward-t8-ngram-speculation-screen"} 322.0
vllm:iteration_tokens_total_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 322.0
vllm:iteration_tokens_total_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 322.0
vllm:iteration_tokens_total_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 55900.0
# 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="tensward-t8-ngram-speculation-screen"} 1.790780013394021e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 2.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 6.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 8.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 14.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="100.0",model_name="tensward-t8-ngram-speculation-screen"} 25.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="200.0",model_name="tensward-t8-ngram-speculation-screen"} 51.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="500.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="1000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="2000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="5000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_max_num_generation_tokens_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_max_num_generation_tokens_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_max_num_generation_tokens_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 4713.0
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133940804e+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="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_n_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_n_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_n_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_n_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_n_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_n_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_n_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133941236e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_params_max_tokens_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_params_max_tokens_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_params_max_tokens_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_params_max_tokens_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_params_max_tokens_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_params_max_tokens_bucket{engine="0",le="100.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_params_max_tokens_bucket{engine="0",le="200.0",model_name="tensward-t8-ngram-speculation-screen"} 36.0
vllm:request_params_max_tokens_bucket{engine="0",le="500.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_max_tokens_bucket{engine="0",le="1000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_max_tokens_bucket{engine="0",le="2000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_max_tokens_bucket{engine="0",le="5000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_max_tokens_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_max_tokens_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_params_max_tokens_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 8704.0
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133941667e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.005",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.01",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.02",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.04",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.06",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.08",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.1",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.25",model_name="tensward-t8-ngram-speculation-screen"} 2.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 8.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.75",model_name="tensward-t8-ngram-speculation-screen"} 9.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 13.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 25.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 39.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="7.5",model_name="tensward-t8-ngram-speculation-screen"} 48.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="80.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="160.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="640.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="2560.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:time_to_first_token_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 163.8738980293274
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133942187e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.025",model_name="tensward-t8-ngram-speculation-screen"} 310.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.05",model_name="tensward-t8-ngram-speculation-screen"} 2008.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.075",model_name="tensward-t8-ngram-speculation-screen"} 3059.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.1",model_name="tensward-t8-ngram-speculation-screen"} 3059.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.15",model_name="tensward-t8-ngram-speculation-screen"} 3059.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.2",model_name="tensward-t8-ngram-speculation-screen"} 3093.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.3",model_name="tensward-t8-ngram-speculation-screen"} 3216.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.4",model_name="tensward-t8-ngram-speculation-screen"} 3278.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 3369.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.75",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="7.5",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="80.0",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 3711.0
vllm:inter_token_latency_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 434.26698424100323
# 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="tensward-t8-ngram-speculation-screen"} 1.790780013394306e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.025",model_name="tensward-t8-ngram-speculation-screen"} 2.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.05",model_name="tensward-t8-ngram-speculation-screen"} 11.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.075",model_name="tensward-t8-ngram-speculation-screen"} 17.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.1",model_name="tensward-t8-ngram-speculation-screen"} 25.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.15",model_name="tensward-t8-ngram-speculation-screen"} 42.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.2",model_name="tensward-t8-ngram-speculation-screen"} 44.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.3",model_name="tensward-t8-ngram-speculation-screen"} 47.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.4",model_name="tensward-t8-ngram-speculation-screen"} 48.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 48.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.75",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="7.5",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="80.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_time_per_output_token_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 7.31639512038728
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133943655e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.8",model_name="tensward-t8-ngram-speculation-screen"} 1.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.5",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 10.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 22.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="15.0",model_name="tensward-t8-ngram-speculation-screen"} 32.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="30.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="60.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="120.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="240.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="480.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="960.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1920.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="7680.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:e2e_request_latency_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 598.1281266212463
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133944247e+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="tensward-t8-ngram-speculation-screen"} 21.0
vllm:request_queue_time_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 21.0
vllm:request_queue_time_seconds_bucket{engine="0",le="0.8",model_name="tensward-t8-ngram-speculation-screen"} 25.0
vllm:request_queue_time_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 25.0
vllm:request_queue_time_seconds_bucket{engine="0",le="1.5",model_name="tensward-t8-ngram-speculation-screen"} 29.0
vllm:request_queue_time_seconds_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 32.0
vllm:request_queue_time_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 37.0
vllm:request_queue_time_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 44.0
vllm:request_queue_time_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="15.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="30.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="60.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="120.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="240.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="480.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="960.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="1920.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="7680.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_queue_time_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 105.2521136600003
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133946733e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_inference_time_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_inference_time_seconds_bucket{engine="0",le="0.8",model_name="tensward-t8-ngram-speculation-screen"} 2.0
vllm:request_inference_time_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:request_inference_time_seconds_bucket{engine="0",le="1.5",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:request_inference_time_seconds_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 6.0
vllm:request_inference_time_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 6.0
vllm:request_inference_time_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 12.0
vllm:request_inference_time_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 29.0
vllm:request_inference_time_seconds_bucket{engine="0",le="15.0",model_name="tensward-t8-ngram-speculation-screen"} 41.0
vllm:request_inference_time_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="30.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="60.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="120.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="240.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="480.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="960.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="1920.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="7680.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_inference_time_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 473.533143241003
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133947625e+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="tensward-t8-ngram-speculation-screen"} 6.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 10.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.8",model_name="tensward-t8-ngram-speculation-screen"} 34.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 34.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.5",model_name="tensward-t8-ngram-speculation-screen"} 50.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 51.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="15.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="30.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="60.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="120.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="240.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="480.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="960.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="1920.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="7680.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_time_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 39.26615899999979
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133948367e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_decode_time_seconds_bucket{engine="0",le="0.5",model_name="tensward-t8-ngram-speculation-screen"} 2.0
vllm:request_decode_time_seconds_bucket{engine="0",le="0.8",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:request_decode_time_seconds_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 3.0
vllm:request_decode_time_seconds_bucket{engine="0",le="1.5",model_name="tensward-t8-ngram-speculation-screen"} 6.0
vllm:request_decode_time_seconds_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 6.0
vllm:request_decode_time_seconds_bucket{engine="0",le="2.5",model_name="tensward-t8-ngram-speculation-screen"} 7.0
vllm:request_decode_time_seconds_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 15.0
vllm:request_decode_time_seconds_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 32.0
vllm:request_decode_time_seconds_bucket{engine="0",le="15.0",model_name="tensward-t8-ngram-speculation-screen"} 44.0
vllm:request_decode_time_seconds_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="30.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="40.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="60.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="120.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="240.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="480.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="960.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="1920.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="7680.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_decode_time_seconds_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 434.26698424100323
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133949063e+09
# HELP vllm:request_num_preemptions Histogram of the number of times a request was preempted.
# TYPE vllm:request_num_preemptions histogram
vllm:request_num_preemptions_bucket{engine="0",le="1.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_bucket{engine="0",le="3.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_bucket{engine="0",le="4.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_num_preemptions_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
# HELP vllm:request_num_preemptions_created Histogram of the number of times a request was preempted.
# TYPE vllm:request_num_preemptions_created gauge
vllm:request_num_preemptions_created{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 1.7907800133949707e+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="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="10.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="20.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="50.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="100.0",model_name="tensward-t8-ngram-speculation-screen"} 0.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="200.0",model_name="tensward-t8-ngram-speculation-screen"} 1.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="500.0",model_name="tensward-t8-ngram-speculation-screen"} 10.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="1000.0",model_name="tensward-t8-ngram-speculation-screen"} 41.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2000.0",model_name="tensward-t8-ngram-speculation-screen"} 47.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5000.0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="+Inf",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_kv_computed_tokens_count{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 52.0
vllm:request_prefill_kv_computed_tokens_sum{engine="0",model_name="tensward-t8-ngram-speculation-screen"} 51187.0
# 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="tensward-t8-ngram-speculation-screen"} 1.7907800133950834e+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="16",cache_dtype="auto",enable_mamba_fine_grained_prefix_cache="False",enable_prefix_caching="False",engine="0",gpu_memory_utilization="0.85",is_attention_free="False",kv_cache_dtype_skip_layers="[]",kv_cache_layout="None",kv_cache_max_concurrency="24.88671875",kv_cache_memory_bytes="None",kv_cache_size_tokens="203872",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="12742",num_gpu_blocks_override="None",prefix_cache_retention_interval="0",prefix_caching_hash_algo="sha256",prefix_match_unit="None",replayssm_buffer_len="16",skip_page_size_padded="None",sliding_window="None",use_kda_recoverssm="False",use_replayssm="False",user_specified_block_size="False",user_specified_mamba_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/models",method="GET",status="2xx"} 1.0
http_requests_total{handler="/tokenize",method="POST",status="2xx"} 120.0
http_requests_total{handler="/v1/chat/completions",method="POST",status="2xx"} 52.0
# HELP http_requests_created Total number of requests by method, status and handler.
# TYPE http_requests_created gauge
http_requests_created{handler="/v1/models",method="GET",status="2xx"} 1.7907800148602529e+09
http_requests_created{handler="/tokenize",method="POST",status="2xx"} 1.7907800148729503e+09
http_requests_created{handler="/v1/chat/completions",method="POST",status="2xx"} 1.7907800196080468e+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/models"} 1.0
http_request_size_bytes_sum{handler="/v1/models"} 0.0
http_request_size_bytes_count{handler="/tokenize"} 120.0
http_request_size_bytes_sum{handler="/tokenize"} 508661.0
http_request_size_bytes_count{handler="/v1/chat/completions"} 52.0
http_request_size_bytes_sum{handler="/v1/chat/completions"} 231725.0
# 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/models"} 1.790780014860288e+09
http_request_size_bytes_created{handler="/tokenize"} 1.7907800148729744e+09
http_request_size_bytes_created{handler="/v1/chat/completions"} 1.7907800196080737e+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/models"} 1.0
http_response_size_bytes_sum{handler="/v1/models"} 542.0
http_response_size_bytes_count{handler="/tokenize"} 120.0
http_response_size_bytes_sum{handler="/tokenize"} 527326.0
http_response_size_bytes_count{handler="/v1/chat/completions"} 52.0
http_response_size_bytes_sum{handler="/v1/chat/completions"} 0.0
# 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/models"} 1.7907800148603187e+09
http_response_size_bytes_created{handler="/tokenize"} 1.790780014873e+09
http_response_size_bytes_created{handler="/v1/chat/completions"} 1.7907800196081014e+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"} 113.0
http_request_duration_highr_seconds_bucket{le="0.025"} 121.0
http_request_duration_highr_seconds_bucket{le="0.05"} 121.0
http_request_duration_highr_seconds_bucket{le="0.075"} 121.0
http_request_duration_highr_seconds_bucket{le="0.1"} 121.0
http_request_duration_highr_seconds_bucket{le="0.25"} 121.0
http_request_duration_highr_seconds_bucket{le="0.5"} 121.0
http_request_duration_highr_seconds_bucket{le="0.75"} 121.0
http_request_duration_highr_seconds_bucket{le="1.0"} 124.0
http_request_duration_highr_seconds_bucket{le="1.5"} 124.0
http_request_duration_highr_seconds_bucket{le="2.0"} 124.0
http_request_duration_highr_seconds_bucket{le="2.5"} 124.0
http_request_duration_highr_seconds_bucket{le="3.0"} 125.0
http_request_duration_highr_seconds_bucket{le="3.5"} 126.0
http_request_duration_highr_seconds_bucket{le="4.0"} 130.0
http_request_duration_highr_seconds_bucket{le="4.5"} 130.0
http_request_duration_highr_seconds_bucket{le="5.0"} 131.0
http_request_duration_highr_seconds_bucket{le="7.5"} 139.0
http_request_duration_highr_seconds_bucket{le="10.0"} 143.0
http_request_duration_highr_seconds_bucket{le="30.0"} 173.0
http_request_duration_highr_seconds_bucket{le="60.0"} 173.0
http_request_duration_highr_seconds_bucket{le="+Inf"} 173.0
http_request_duration_highr_seconds_count 173.0
http_request_duration_highr_seconds_sum 599.6389711400016
# 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 1.7907800136235943e+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/models",le="0.1",method="GET"} 1.0
http_request_duration_seconds_bucket{handler="/v1/models",le="0.5",method="GET"} 1.0
http_request_duration_seconds_bucket{handler="/v1/models",le="1.0",method="GET"} 1.0
http_request_duration_seconds_bucket{handler="/v1/models",le="+Inf",method="GET"} 1.0
http_request_duration_seconds_count{handler="/v1/models",method="GET"} 1.0
http_request_duration_seconds_sum{handler="/v1/models",method="GET"} 0.002032478999808518
http_request_duration_seconds_bucket{handler="/tokenize",le="0.1",method="POST"} 120.0
http_request_duration_seconds_bucket{handler="/tokenize",le="0.5",method="POST"} 120.0
http_request_duration_seconds_bucket{handler="/tokenize",le="1.0",method="POST"} 120.0
http_request_duration_seconds_bucket{handler="/tokenize",le="+Inf",method="POST"} 120.0
http_request_duration_seconds_count{handler="/tokenize",method="POST"} 120.0
http_request_duration_seconds_sum{handler="/tokenize",method="POST"} 0.5948938180017649
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="0.1",method="POST"} 0.0
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="0.5",method="POST"} 0.0
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="1.0",method="POST"} 3.0
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="+Inf",method="POST"} 52.0
http_request_duration_seconds_count{handler="/v1/chat/completions",method="POST"} 52.0
http_request_duration_seconds_sum{handler="/v1/chat/completions",method="POST"} 599.042044843
# 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/models",method="GET"} 1.7907800148603604e+09
http_request_duration_seconds_created{handler="/tokenize",method="POST"} 1.7907800148730295e+09
http_request_duration_seconds_created{handler="/v1/chat/completions",method="POST"} 1.790780019608134e+09
# HELP vllm:tool_call_parser_invocations_total Total number of ToolParser invocations. Non-streaming increments once per choice; streaming increments once per delta.
# TYPE vllm:tool_call_parser_invocations_total counter
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="chat_completions"} 1077.0
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="responses"} 0.0
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="other"} 0.0
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="chat_completions"} 248.0
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="responses"} 0.0
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="other"} 0.0
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="chat_completions"} 0.0
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="responses"} 0.0
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="other"} 0.0
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="chat_completions"} 0.0
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="responses"} 0.0
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="other"} 0.0
# HELP vllm:tool_call_parser_invocations_created Total number of ToolParser invocations. Non-streaming increments once per choice; streaming increments once per delta.
# TYPE vllm:tool_call_parser_invocations_created gauge
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="chat_completions"} 1.7907800136245425e+09
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="responses"} 1.7907800136245575e+09
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="other"} 1.7907800136245692e+09
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="chat_completions"} 1.7907800136245794e+09
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="responses"} 1.7907800136245887e+09
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="other"} 1.7907800136245985e+09
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="chat_completions"} 1.7907800136246078e+09
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="responses"} 1.7907800136246161e+09
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="tool_call",request_type="other"} 1.7907800136246252e+09
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="chat_completions"} 1.790780013624634e+09
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="responses"} 1.7907800136246433e+09
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="tensward-t8-ngram-speculation-screen",outcome="no_tool_call",request_type="other"} 1.7907800136246526e+09
