Add homelab dashboards: system, LLM, and UPS on one domain
Three dashboards served by one FastAPI app with a SQLite history store
(raw / 1m / 1h) and hand-written SVG charts: no Prometheus, no Grafana,
no CDN, no build step. Nothing is fetched from the internet at runtime.
* system: a stdlib-only agent (agent/host_agent.py) reports /proc and
/sys counters; the dashboard turns them into rates over a labelled
window, so every number says how it was measured.
* llm: gufo/llama.cpp and vLLM /metrics are parsed by an in-house
exposition parser. Measured delta/elapsed throughput beats a native
per-request gauge, and each value carries its provenance.
* ups: a NUT wire-protocol client plus health checks that name what
they looked at. Commands are gated by NUT_ALLOW_ACTIONS,
DASH_READ_ONLY and a DANGER confirmation, re-checked server-side.
Missing values render as n/a rather than 0, and an unconfigured source
answers 404 {"configured": false} without dialling anything, so "not
deployed here" never looks like an outage.
253 tests at 94% coverage against captured real fixtures; ruff and
pyright clean.
LLM-Generated: true
This commit is contained in:
Vendored
+1
File diff suppressed because one or more lines are too long
+1
File diff suppressed because one or more lines are too long
Vendored
+1
@@ -0,0 +1 @@
|
||||
{"ok": true, "schema": 1, "agent_version": "1.0.0", "ts": 1792178443.0656452, "duration_ms": 10.22, "host": {"hostname": "gateway", "os_pretty": "AlmaLinux 10.2 (Lavender Lion)", "os_id": "almalinux", "kernel": "6.12.0-211.65.1.el10_2.x86_64_v2", "arch": "x86_64", "python": "3.12.15", "cpu_model": "AMD Ryzen Threadripper 3960X 24-Core Processor", "cpu_cores_logical": 2, "cpu_cores_physical": 2, "memory_total_bytes": 2051493888.0, "boot_ts": 1791967457.1014743, "uptime_seconds": 210985.95, "container": false, "agent_version": "1.0.0"}, "cpu": {"modes": {"user": 561498.0, "nice": 2756.0, "system": 122750.0, "idle": 41118362.0, "iowait": 290460.0, "irq": 24373.0, "softirq": 46665.0, "steal": 4918.0, "guest": 0.0, "guest_nice": 0.0, "total": 42171782.0}, "cores": [{"core": 0, "modes": {"user": 285993.0, "nice": 1771.0, "system": 60082.0, "idle": 20538975.0, "iowait": 143245.0, "irq": 14642.0, "softirq": 38622.0, "steal": 3640.0, "guest": 0.0, "guest_nice": 0.0, "total": 21086970.0}}, {"core": 1, "modes": {"user": 275504.0, "nice": 985.0, "system": 62667.0, "idle": 20579386.0, "iowait": 147214.0, "irq": 9730.0, "softirq": 8043.0, "steal": 1277.0, "guest": 0.0, "guest_nice": 0.0, "total": 21084806.0}}], "clock_ticks_per_second": 100, "load1": 0.01, "load5": 0.07, "load15": 0.08, "procs_running": 1.0, "procs_blocked": 2.0, "ctxt_total": 64391428.0, "processes_total": 343402.0, "freq_mhz": null, "freq_max_mhz": null}, "memory": {"total_bytes": 2051493888.0, "free_bytes": 172544000.0, "available_bytes": 1400086528.0, "used_bytes": 651407360.0, "buffers_bytes": 106156032.0, "cached_bytes": 1315049472.0, "dirty_bytes": 2158592.0, "swap_total_bytes": 0.0, "swap_used_bytes": 0.0, "committed_bytes": 720392192.0}, "filesystems": [{"device": "/dev/vda4", "mountpoint": "/", "fstype": "ext4", "total_bytes": 9197531136, "used_bytes": 5252460544, "free_bytes": 3455754240, "used_pct": 60.316157493618384, "read_only": false}, {"device": "/dev/vda3", "mountpoint": "/boot", "fstype": "ext4", "total_bytes": 1020702720, "used_bytes": 272543744, "free_bytes": 677695488, "used_pct": 28.68159246870582, "read_only": false}, {"device": "/dev/vda2", "mountpoint": "/boot/efi", "fstype": "vfat", "total_bytes": 209489920, "used_bytes": 9560064, "free_bytes": 199929856, "used_pct": 4.56349594290742, "read_only": false}], "disk_io": {"devices": [{"name": "vda", "model": null, "rotational": true, "size_bytes": 10737418240.0, "reads_total": 14464.0, "writes_total": 1989589.0, "read_bytes_total": 645659136.0, "write_bytes_total": 22551089664.0, "in_flight": 0.0, "io_time_ms_total": 2882080.0, "weighted_io_ms_total": 6688324.0, "discard_bytes_total": 0.0}], "device_names": ["vda"]}, "network": {"interfaces": [{"name": "eth0", "rx_bytes_total": 14580699012.0, "rx_packets_total": 22626423.0, "rx_errors_total": 0.0, "rx_dropped_total": 287.0, "tx_bytes_total": 10807075678.0, "tx_packets_total": 10084825.0, "tx_errors_total": 0.0, "tx_dropped_total": 0.0, "speed_mbps": null}]}, "gpus": [], "temperatures": [], "cpu_temperature_celsius": null, "processes": {"total": 142, "top_rss": [{"pid": 592, "name": "systemd-journal", "rss_bytes": 105857024.0}, {"pid": 1182, "name": "haproxy", "rss_bytes": 99045376.0}, {"pid": 723, "name": "firewalld", "rss_bytes": 45318144.0}, {"pid": 1091, "name": "polkitd", "rss_bytes": 41594880.0}, {"pid": 1, "name": "systemd", "rss_bytes": 37564416.0}], "top_cpu": [{"pid": 342784, "name": "python3", "cpu_pct": 2.680722502695548}, {"pid": 1, "name": "systemd", "cpu_pct": 0.0}, {"pid": 2, "name": "kthreadd", "cpu_pct": 0.0}, {"pid": 3, "name": "pool_workqueue_release", "cpu_pct": 0.0}, {"pid": 4, "name": "kworker/R-rcu_gp", "cpu_pct": 0.0}]}, "errors": []}
|
||||
Vendored
+45
@@ -0,0 +1,45 @@
|
||||
# HELP gufo_device_lost_total Confirmed GPU context losses
|
||||
# TYPE gufo_device_lost_total counter
|
||||
gufo_device_lost_total 0
|
||||
# HELP llamacpp:prompt_tokens_total Total prompt tokens processed, excluding cache hits
|
||||
# TYPE llamacpp:prompt_tokens_total counter
|
||||
llamacpp:prompt_tokens_total 1350666
|
||||
# HELP llamacpp:prompt_tokens_cached_total Total prompt tokens reused from cache
|
||||
# TYPE llamacpp:prompt_tokens_cached_total counter
|
||||
llamacpp:prompt_tokens_cached_total 124529105
|
||||
# HELP llamacpp:prompt_seconds_total Prompt process time
|
||||
# TYPE llamacpp:prompt_seconds_total counter
|
||||
llamacpp:prompt_seconds_total 1478.1443332270005
|
||||
# HELP llamacpp:tokens_predicted_total Total tokens generated
|
||||
# TYPE llamacpp:tokens_predicted_total counter
|
||||
llamacpp:tokens_predicted_total 877336
|
||||
# HELP llamacpp:tokens_predicted_seconds_total Predict process time
|
||||
# TYPE llamacpp:tokens_predicted_seconds_total counter
|
||||
llamacpp:tokens_predicted_seconds_total 26565.247833160014
|
||||
# HELP llamacpp:n_tokens_max Largest observed n_tokens.
|
||||
# TYPE llamacpp:n_tokens_max counter
|
||||
llamacpp:n_tokens_max 252622
|
||||
# HELP llamacpp:spec_decode_num_drafts_total Total speculative verification rounds
|
||||
# TYPE llamacpp:spec_decode_num_drafts_total counter
|
||||
llamacpp:spec_decode_num_drafts_total 291738
|
||||
# HELP llamacpp:spec_decode_num_draft_tokens_total Total draft tokens proposed
|
||||
# TYPE llamacpp:spec_decode_num_draft_tokens_total counter
|
||||
llamacpp:spec_decode_num_draft_tokens_total 789028
|
||||
# HELP llamacpp:spec_decode_num_accepted_tokens_total Total draft tokens accepted
|
||||
# TYPE llamacpp:spec_decode_num_accepted_tokens_total counter
|
||||
llamacpp:spec_decode_num_accepted_tokens_total 578514
|
||||
# HELP llamacpp:prompt_tokens_seconds Prompt processing speed in tokens per second
|
||||
# TYPE llamacpp:prompt_tokens_seconds gauge
|
||||
llamacpp:prompt_tokens_seconds 160.47362399350274
|
||||
# HELP llamacpp:predicted_tokens_seconds Generation speed in tokens per second
|
||||
# TYPE llamacpp:predicted_tokens_seconds gauge
|
||||
llamacpp:predicted_tokens_seconds 42.621031668072597
|
||||
# HELP llamacpp:requests_processing Number of admitted requests, including cache preparation
|
||||
# TYPE llamacpp:requests_processing gauge
|
||||
llamacpp:requests_processing 0
|
||||
# HELP llamacpp:requests_deferred Number of requests waiting for a session
|
||||
# TYPE llamacpp:requests_deferred gauge
|
||||
llamacpp:requests_deferred 0
|
||||
# HELP llamacpp:kv_cache_usage_ratio In-flight prompt and generated tokens over sessions times context; excludes retained cache
|
||||
# TYPE llamacpp:kv_cache_usage_ratio gauge
|
||||
llamacpp:kv_cache_usage_ratio 0
|
||||
Vendored
+662
@@ -0,0 +1,662 @@
|
||||
# HELP python_gc_objects_collected_total Objects collected during gc
|
||||
# TYPE python_gc_objects_collected_total counter
|
||||
python_gc_objects_collected_total{generation="0"} 166913.0
|
||||
python_gc_objects_collected_total{generation="1"} 27377.0
|
||||
python_gc_objects_collected_total{generation="2"} 1409.0
|
||||
# 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"} 4631.0
|
||||
python_gc_collections_total{generation="1"} 420.0
|
||||
python_gc_collections_total{generation="2"} 12.0
|
||||
# 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 3.2837738496e+10
|
||||
# HELP process_resident_memory_bytes Resident memory size in bytes.
|
||||
# TYPE process_resident_memory_bytes gauge
|
||||
process_resident_memory_bytes 2.370977792e+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 1.79210782535e+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 457.6
|
||||
# HELP process_open_fds Number of open file descriptors.
|
||||
# TYPE process_open_fds gauge
|
||||
process_open_fds 43.0
|
||||
# HELP process_max_fds Maximum number of open file descriptors.
|
||||
# TYPE process_max_fds gauge
|
||||
process_max_fds 524288.0
|
||||
# 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="juggernaut"} 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="juggernaut"} 1.7921081022034154e+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="juggernaut"} 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="juggernaut"} 1.792108102203435e+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="juggernaut"} 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="juggernaut"} 1.7921081022034492e+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="juggernaut"} 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="juggernaut"} 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="juggernaut",reason="capacity"} 0.0
|
||||
vllm:num_requests_waiting_by_reason{engine="0",model_name="juggernaut",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="juggernaut",sleep_state="awake"} 1.0
|
||||
vllm:engine_sleep_state{engine="0",model_name="juggernaut",sleep_state="weights_offloaded"} 0.0
|
||||
vllm:engine_sleep_state{engine="0",model_name="juggernaut",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="juggernaut"} 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="juggernaut"} 1.8389909e+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="juggernaut"} 1.7921081022037191e+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="juggernaut"} 1.210496e+07
|
||||
# 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="juggernaut"} 1.792108102203731e+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="juggernaut"} 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="juggernaut"} 1.7921081022037423e+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="juggernaut"} 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="juggernaut"} 1.792108102203755e+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="juggernaut"} 8.0
|
||||
# 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="juggernaut"} 1.7921081022037659e+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="juggernaut"} 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="juggernaut"} 1.7921081022037778e+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="juggernaut"} 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="juggernaut"} 1.7921081022037895e+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="juggernaut"} 1.8389909e+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="juggernaut"} 1.7921081022038019e+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="juggernaut",source="local_compute"} 6.284949e+06
|
||||
vllm:prompt_tokens_by_source_total{engine="0",model_name="juggernaut",source="local_cache_hit"} 1.210496e+07
|
||||
vllm:prompt_tokens_by_source_total{engine="0",model_name="juggernaut",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="juggernaut",source="local_compute"} 1.7921081022038164e+09
|
||||
vllm:prompt_tokens_by_source_created{engine="0",model_name="juggernaut",source="local_cache_hit"} 1.7921081022038229e+09
|
||||
vllm:prompt_tokens_by_source_created{engine="0",model_name="juggernaut",source="external_kv_transfer"} 1.7921081022038274e+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="juggernaut"} 1.210496e+07
|
||||
# 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="juggernaut"} 1.7921081022038393e+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="juggernaut"} 611163.0
|
||||
# HELP vllm:generation_tokens_created Number of generation tokens processed.
|
||||
# TYPE vllm:generation_tokens_created gauge
|
||||
vllm:generation_tokens_created{engine="0",model_name="juggernaut"} 1.7921081022038517e+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="juggernaut"} 3488.0
|
||||
vllm:request_success_total{engine="0",finished_reason="length",model_name="juggernaut"} 0.0
|
||||
vllm:request_success_total{engine="0",finished_reason="abort",model_name="juggernaut"} 0.0
|
||||
vllm:request_success_total{engine="0",finished_reason="error",model_name="juggernaut"} 0.0
|
||||
vllm:request_success_total{engine="0",finished_reason="repetition",model_name="juggernaut"} 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="juggernaut"} 1.792108102203872e+09
|
||||
vllm:request_success_created{engine="0",finished_reason="length",model_name="juggernaut"} 1.7921081022038789e+09
|
||||
vllm:request_success_created{engine="0",finished_reason="abort",model_name="juggernaut"} 1.7921081022038846e+09
|
||||
vllm:request_success_created{engine="0",finished_reason="error",model_name="juggernaut"} 1.7921081022038896e+09
|
||||
vllm:request_success_created{engine="0",finished_reason="repetition",model_name="juggernaut"} 1.7921081022038949e+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="juggernaut"} 0.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="2.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="5.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="10.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="20.0",model_name="juggernaut"} 5.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="50.0",model_name="juggernaut"} 5.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="100.0",model_name="juggernaut"} 30.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="200.0",model_name="juggernaut"} 133.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="500.0",model_name="juggernaut"} 612.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="1000.0",model_name="juggernaut"} 1135.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="2000.0",model_name="juggernaut"} 2002.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="5000.0",model_name="juggernaut"} 3126.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="10000.0",model_name="juggernaut"} 3227.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="20000.0",model_name="juggernaut"} 3290.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="50000.0",model_name="juggernaut"} 3383.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="100000.0",model_name="juggernaut"} 3482.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prompt_tokens_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prompt_tokens_sum{engine="0",model_name="juggernaut"} 1.8352277e+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="juggernaut"} 1.7921081022039344e+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="juggernaut"} 0.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="2.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="5.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="10.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="20.0",model_name="juggernaut"} 6.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="50.0",model_name="juggernaut"} 45.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="100.0",model_name="juggernaut"} 819.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="200.0",model_name="juggernaut"} 3206.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="500.0",model_name="juggernaut"} 3379.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="1000.0",model_name="juggernaut"} 3423.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="2000.0",model_name="juggernaut"} 3464.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="5000.0",model_name="juggernaut"} 3486.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="10000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="20000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="50000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="100000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_generation_tokens_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_generation_tokens_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_generation_tokens_sum{engine="0",model_name="juggernaut"} 610140.0
|
||||
# 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="juggernaut"} 1.7921081022039804e+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="juggernaut"} 317139.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="8.0",model_name="juggernaut"} 461626.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="16.0",model_name="juggernaut"} 461631.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="32.0",model_name="juggernaut"} 461631.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="64.0",model_name="juggernaut"} 461632.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="128.0",model_name="juggernaut"} 461692.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="256.0",model_name="juggernaut"} 461852.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="512.0",model_name="juggernaut"} 462266.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="1024.0",model_name="juggernaut"} 462849.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="2048.0",model_name="juggernaut"} 463840.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="4096.0",model_name="juggernaut"} 464991.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="8192.0",model_name="juggernaut"} 465088.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="16384.0",model_name="juggernaut"} 465097.0
|
||||
vllm:iteration_tokens_total_bucket{engine="0",le="+Inf",model_name="juggernaut"} 465099.0
|
||||
vllm:iteration_tokens_total_count{engine="0",model_name="juggernaut"} 465099.0
|
||||
vllm:iteration_tokens_total_sum{engine="0",model_name="juggernaut"} 6.896112e+06
|
||||
# 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="juggernaut"} 1.7921081022040136e+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="juggernaut"} 0.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="2.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="5.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="10.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="20.0",model_name="juggernaut"} 6.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="50.0",model_name="juggernaut"} 45.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="100.0",model_name="juggernaut"} 819.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="200.0",model_name="juggernaut"} 3206.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="500.0",model_name="juggernaut"} 3379.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="1000.0",model_name="juggernaut"} 3423.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="2000.0",model_name="juggernaut"} 3464.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="5000.0",model_name="juggernaut"} 3486.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="10000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="20000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="50000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="100000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_max_num_generation_tokens_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_max_num_generation_tokens_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_max_num_generation_tokens_sum{engine="0",model_name="juggernaut"} 610140.0
|
||||
# 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="juggernaut"} 1.7921081022040458e+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="juggernaut"} 3488.0
|
||||
vllm:request_params_n_bucket{engine="0",le="2.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_n_bucket{engine="0",le="5.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_n_bucket{engine="0",le="10.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_n_bucket{engine="0",le="20.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_n_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_n_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_n_sum{engine="0",model_name="juggernaut"} 3488.0
|
||||
# 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="juggernaut"} 1.7921081022040787e+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="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="2.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="5.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="10.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="20.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="50.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="100.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="200.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="500.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="1000.0",model_name="juggernaut"} 1.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="2000.0",model_name="juggernaut"} 1.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="5000.0",model_name="juggernaut"} 3139.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="10000.0",model_name="juggernaut"} 3140.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="20000.0",model_name="juggernaut"} 3183.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="50000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="100000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_max_tokens_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_max_tokens_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_params_max_tokens_sum{engine="0",model_name="juggernaut"} 1.7011909e+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="juggernaut"} 1.7921081022041035e+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="juggernaut"} 0.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.005",model_name="juggernaut"} 0.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.01",model_name="juggernaut"} 0.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.02",model_name="juggernaut"} 0.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.04",model_name="juggernaut"} 0.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.06",model_name="juggernaut"} 0.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.08",model_name="juggernaut"} 4.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.1",model_name="juggernaut"} 4.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.25",model_name="juggernaut"} 592.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 1312.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.75",model_name="juggernaut"} 1924.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 2266.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 3433.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 3485.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="7.5",model_name="juggernaut"} 3488.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 3489.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="80.0",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="160.0",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="640.0",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="2560.0",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_count{engine="0",model_name="juggernaut"} 3490.0
|
||||
vllm:time_to_first_token_seconds_sum{engine="0",model_name="juggernaut"} 2904.5298397541046
|
||||
# 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="juggernaut"} 1.7921081022041366e+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="juggernaut"} 0.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.025",model_name="juggernaut"} 0.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.05",model_name="juggernaut"} 596060.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.075",model_name="juggernaut"} 605658.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.1",model_name="juggernaut"} 605758.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.15",model_name="juggernaut"} 606021.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.2",model_name="juggernaut"} 606268.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.3",model_name="juggernaut"} 606488.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.4",model_name="juggernaut"} 606669.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 606814.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.75",model_name="juggernaut"} 607341.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 607398.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="7.5",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="80.0",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_count{engine="0",model_name="juggernaut"} 607673.0
|
||||
vllm:inter_token_latency_seconds_sum{engine="0",model_name="juggernaut"} 22579.6616614901
|
||||
# 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="juggernaut"} 1.7921081022041779e+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="juggernaut"} 0.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.025",model_name="juggernaut"} 0.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.05",model_name="juggernaut"} 3383.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.075",model_name="juggernaut"} 3485.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.1",model_name="juggernaut"} 3487.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.15",model_name="juggernaut"} 3487.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.2",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.3",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.4",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="0.75",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="7.5",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="80.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_time_per_output_token_seconds_sum{engine="0",model_name="juggernaut"} 125.03691733873717
|
||||
# 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="juggernaut"} 1.7921081022042146e+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="juggernaut"} 0.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 2.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="0.8",model_name="juggernaut"} 5.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 5.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1.5",model_name="juggernaut"} 14.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.0",model_name="juggernaut"} 57.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 211.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 1389.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 3241.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="15.0",model_name="juggernaut"} 3339.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 3369.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="30.0",model_name="juggernaut"} 3404.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 3418.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="50.0",model_name="juggernaut"} 3436.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="60.0",model_name="juggernaut"} 3449.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="120.0",model_name="juggernaut"} 3480.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="240.0",model_name="juggernaut"} 3486.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="480.0",model_name="juggernaut"} 3488.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="960.0",model_name="juggernaut"} 3488.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="1920.0",model_name="juggernaut"} 3488.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="7680.0",model_name="juggernaut"} 3488.0
|
||||
vllm:e2e_request_latency_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:e2e_request_latency_seconds_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:e2e_request_latency_seconds_sum{engine="0",model_name="juggernaut"} 25442.03079867363
|
||||
# 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="juggernaut"} 1.7921081022042491e+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="juggernaut"} 3485.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 3485.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="0.8",model_name="juggernaut"} 3485.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 3485.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="1.5",model_name="juggernaut"} 3487.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="2.0",model_name="juggernaut"} 3487.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 3487.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="15.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="30.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="50.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="60.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="120.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="240.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="480.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="960.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="1920.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="7680.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_queue_time_seconds_sum{engine="0",model_name="juggernaut"} 6.650666017842013
|
||||
# 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="juggernaut"} 1.7921081022042854e+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="juggernaut"} 0.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 2.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="0.8",model_name="juggernaut"} 6.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 6.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="1.5",model_name="juggernaut"} 14.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="2.0",model_name="juggernaut"} 61.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 214.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 1394.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 3248.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="15.0",model_name="juggernaut"} 3339.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 3369.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="30.0",model_name="juggernaut"} 3404.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 3418.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="50.0",model_name="juggernaut"} 3436.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="60.0",model_name="juggernaut"} 3449.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="120.0",model_name="juggernaut"} 3480.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="240.0",model_name="juggernaut"} 3486.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="480.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="960.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="1920.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="7680.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_inference_time_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_inference_time_seconds_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_inference_time_seconds_sum{engine="0",model_name="juggernaut"} 25331.654430066672
|
||||
# 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="juggernaut"} 1.79210810220433e+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="juggernaut"} 844.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 1341.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.8",model_name="juggernaut"} 2035.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 2314.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.5",model_name="juggernaut"} 3230.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.0",model_name="juggernaut"} 3384.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 3444.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 3484.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 3487.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="15.0",model_name="juggernaut"} 3487.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="30.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="50.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="60.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="120.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="240.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="480.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="960.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="1920.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="7680.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_time_seconds_sum{engine="0",model_name="juggernaut"} 2786.310553313582
|
||||
# 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="juggernaut"} 1.7921081022043684e+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="juggernaut"} 0.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 4.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="0.8",model_name="juggernaut"} 6.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 7.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="1.5",model_name="juggernaut"} 22.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="2.0",model_name="juggernaut"} 165.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 452.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 2092.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 3278.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="15.0",model_name="juggernaut"} 3354.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 3376.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="30.0",model_name="juggernaut"} 3406.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 3422.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="50.0",model_name="juggernaut"} 3438.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="60.0",model_name="juggernaut"} 3450.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="120.0",model_name="juggernaut"} 3481.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="240.0",model_name="juggernaut"} 3486.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="480.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="960.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="1920.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="7680.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_decode_time_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_decode_time_seconds_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_decode_time_seconds_sum{engine="0",model_name="juggernaut"} 22545.34387675309
|
||||
# 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="juggernaut"} 1.7921081022044446e+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="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_bucket{engine="0",le="2.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_bucket{engine="0",le="3.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_bucket{engine="0",le="4.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_bucket{engine="0",le="5.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_bucket{engine="0",le="10.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_bucket{engine="0",le="20.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_num_preemptions_sum{engine="0",model_name="juggernaut"} 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="juggernaut"} 1.792108102204479e+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="juggernaut"} 0.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="10.0",model_name="juggernaut"} 0.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="20.0",model_name="juggernaut"} 5.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="50.0",model_name="juggernaut"} 6.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="100.0",model_name="juggernaut"} 32.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="200.0",model_name="juggernaut"} 136.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="500.0",model_name="juggernaut"} 628.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="1000.0",model_name="juggernaut"} 1206.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="2000.0",model_name="juggernaut"} 2210.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="5000.0",model_name="juggernaut"} 3423.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="10000.0",model_name="juggernaut"} 3485.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="20000.0",model_name="juggernaut"} 3486.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="50000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="100000.0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_kv_computed_tokens_bucket{engine="0",le="+Inf",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_kv_computed_tokens_count{engine="0",model_name="juggernaut"} 3488.0
|
||||
vllm:request_prefill_kv_computed_tokens_sum{engine="0",model_name="juggernaut"} 6.267701e+06
|
||||
# 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="juggernaut"} 1.7921081022045038e+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="1568",cache_dtype="fp8",enable_mamba_fine_grained_prefix_cache="False",enable_prefix_caching="True",engine="0",gpu_memory_utilization="0.95",is_attention_free="False",kv_cache_dtype_skip_layers="[]",kv_cache_layout="None",kv_cache_max_concurrency="2.1333333333333333",kv_cache_memory_bytes="None",kv_cache_size_tokens="279620",kv_offloading_backend="native",kv_offloading_size="None",kv_sharing_fast_prefill="False",mamba_block_size="1568",mamba_cache_dtype="auto",mamba_cache_mode="align",mamba_page_size_padded="None",mamba_ssm_cache_dtype="float32",num_cpu_blocks="None",num_gpu_blocks="192",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"} 236.0
|
||||
http_requests_total{handler="/v1/chat/completions",method="POST",status="2xx"} 3490.0
|
||||
http_requests_total{handler="/v1/chat/completions",method="POST",status="4xx"} 1.0
|
||||
# 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"} 1.7921081971217349e+09
|
||||
http_requests_created{handler="/v1/chat/completions",method="POST",status="2xx"} 1.792108217381334e+09
|
||||
http_requests_created{handler="/v1/chat/completions",method="POST",status="4xx"} 1.7921641238703468e+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"} 236.0
|
||||
http_request_size_bytes_sum{handler="/v1/models"} 0.0
|
||||
http_request_size_bytes_count{handler="/v1/chat/completions"} 3491.0
|
||||
http_request_size_bytes_sum{handler="/v1/chat/completions"} 7.4767849e+07
|
||||
# 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"} 1.7921081971218035e+09
|
||||
http_request_size_bytes_created{handler="/v1/chat/completions"} 1.7921082173813493e+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"} 236.0
|
||||
http_response_size_bytes_sum{handler="/v1/models"} 113516.0
|
||||
http_response_size_bytes_count{handler="/v1/chat/completions"} 3491.0
|
||||
http_response_size_bytes_sum{handler="/v1/chat/completions"} 4.443412e+06
|
||||
# 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"} 1.7921081971218395e+09
|
||||
http_response_size_bytes_created{handler="/v1/chat/completions"} 1.7921082173813689e+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"} 236.0
|
||||
http_request_duration_highr_seconds_bucket{le="0.025"} 236.0
|
||||
http_request_duration_highr_seconds_bucket{le="0.05"} 236.0
|
||||
http_request_duration_highr_seconds_bucket{le="0.075"} 236.0
|
||||
http_request_duration_highr_seconds_bucket{le="0.1"} 236.0
|
||||
http_request_duration_highr_seconds_bucket{le="0.25"} 237.0
|
||||
http_request_duration_highr_seconds_bucket{le="0.5"} 239.0
|
||||
http_request_duration_highr_seconds_bucket{le="0.75"} 241.0
|
||||
http_request_duration_highr_seconds_bucket{le="1.0"} 242.0
|
||||
http_request_duration_highr_seconds_bucket{le="1.5"} 251.0
|
||||
http_request_duration_highr_seconds_bucket{le="2.0"} 294.0
|
||||
http_request_duration_highr_seconds_bucket{le="2.5"} 446.0
|
||||
http_request_duration_highr_seconds_bucket{le="3.0"} 678.0
|
||||
http_request_duration_highr_seconds_bucket{le="3.5"} 917.0
|
||||
http_request_duration_highr_seconds_bucket{le="4.0"} 1126.0
|
||||
http_request_duration_highr_seconds_bucket{le="4.5"} 1351.0
|
||||
http_request_duration_highr_seconds_bucket{le="5.0"} 1625.0
|
||||
http_request_duration_highr_seconds_bucket{le="7.5"} 3191.0
|
||||
http_request_duration_highr_seconds_bucket{le="10.0"} 3478.0
|
||||
http_request_duration_highr_seconds_bucket{le="30.0"} 3643.0
|
||||
http_request_duration_highr_seconds_bucket{le="60.0"} 3688.0
|
||||
http_request_duration_highr_seconds_bucket{le="+Inf"} 3727.0
|
||||
http_request_duration_highr_seconds_count 3727.0
|
||||
http_request_duration_highr_seconds_sum 25494.72712990234
|
||||
# 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 1.7921081024104605e+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"} 236.0
|
||||
http_request_duration_seconds_bucket{handler="/v1/models",le="0.5",method="GET"} 236.0
|
||||
http_request_duration_seconds_bucket{handler="/v1/models",le="1.0",method="GET"} 236.0
|
||||
http_request_duration_seconds_bucket{handler="/v1/models",le="+Inf",method="GET"} 236.0
|
||||
http_request_duration_seconds_count{handler="/v1/models",method="GET"} 236.0
|
||||
http_request_duration_seconds_sum{handler="/v1/models",method="GET"} 0.09283922897884622
|
||||
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"} 3.0
|
||||
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="1.0",method="POST"} 6.0
|
||||
http_request_duration_seconds_bucket{handler="/v1/chat/completions",le="+Inf",method="POST"} 3491.0
|
||||
http_request_duration_seconds_count{handler="/v1/chat/completions",method="POST"} 3491.0
|
||||
http_request_duration_seconds_sum{handler="/v1/chat/completions",method="POST"} 25494.634290673363
|
||||
# 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"} 1.7921081971218753e+09
|
||||
http_request_duration_seconds_created{handler="/v1/chat/completions",method="POST"} 1.7921082173813894e+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="juggernaut",outcome="tool_call",request_type="chat_completions"} 31000.0
|
||||
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="juggernaut",outcome="tool_call",request_type="responses"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="juggernaut",outcome="tool_call",request_type="other"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="juggernaut",outcome="no_tool_call",request_type="chat_completions"} 42734.0
|
||||
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="juggernaut",outcome="no_tool_call",request_type="responses"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="streaming",model_name="juggernaut",outcome="no_tool_call",request_type="other"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="juggernaut",outcome="tool_call",request_type="chat_completions"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="juggernaut",outcome="tool_call",request_type="responses"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="juggernaut",outcome="tool_call",request_type="other"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="juggernaut",outcome="no_tool_call",request_type="chat_completions"} 3139.0
|
||||
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="juggernaut",outcome="no_tool_call",request_type="responses"} 0.0
|
||||
vllm:tool_call_parser_invocations_total{mode="non_streaming",model_name="juggernaut",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="juggernaut",outcome="tool_call",request_type="chat_completions"} 1.7921081024108987e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="juggernaut",outcome="tool_call",request_type="responses"} 1.792108102410908e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="juggernaut",outcome="tool_call",request_type="other"} 1.7921081024109144e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="juggernaut",outcome="no_tool_call",request_type="chat_completions"} 1.7921081024109201e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="juggernaut",outcome="no_tool_call",request_type="responses"} 1.7921081024109259e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="streaming",model_name="juggernaut",outcome="no_tool_call",request_type="other"} 1.792108102410931e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="juggernaut",outcome="tool_call",request_type="chat_completions"} 1.7921081024109368e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="juggernaut",outcome="tool_call",request_type="responses"} 1.7921081024109426e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="juggernaut",outcome="tool_call",request_type="other"} 1.7921081024109476e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="juggernaut",outcome="no_tool_call",request_type="chat_completions"} 1.792108102410953e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="juggernaut",outcome="no_tool_call",request_type="responses"} 1.7921081024109583e+09
|
||||
vllm:tool_call_parser_invocations_created{mode="non_streaming",model_name="juggernaut",outcome="no_tool_call",request_type="other"} 1.7921081024109638e+09
|
||||
Reference in New Issue
Block a user