initial import: read-only gufo + vLLM dashboard
Build and Push Container / build-and-push (push) Successful in 38s
Build and Push Container / build-and-push (push) Successful in 38s
Single-file FastAPI proxy plus a no-CDN vanilla-JS page for watching a gufo
server and a vLLM server side by side: one Prometheus parser (class Prom) with
per-engine field maps, measured Δcounter/Δt rates for engines that export no
rate gauge, and strict read-only GET-only routing. Engines are opt-in via
*_BASE_URL — unset means no panel, no poll, and a 404 {"configured": false}
without dialling.
Includes the container image and CI so the dashboard can be deployed as an
image rather than a checkout:
- Containerfile: uv-locked two-stage build on python:3.14-slim, non-root
(uid 10001), binds 8090 (8000 is vLLM's port in this fleet), healthcheck on
/api/config so a dead engine never marks the dashboard unhealthy. No frontend
build stage — static/index.html is bundler-free by design and is copied as-is.
- .gitea/workflows/build-and-push.yml: publishes
gitea.reeseapps.com/Experimental/llm-monitor on main + release tags.
114 tests, no network and no real engines required.
LLM-Generated: true
This commit is contained in:
Vendored
+49
@@ -0,0 +1,49 @@
|
||||
# Captured verbatim from http://deskwork.reeselink.com:8731/metrics (gufo 0.16.0, Qwen3.8 Flash Next,
|
||||
# --sessions 2, --speculative mtp). Re-capture after an engine upgrade; see tests/test_real_contracts.py.
|
||||
# Values are point-in-time and drift between captures — assert on names/sources, not exact numbers.
|
||||
|
||||
# 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 374263
|
||||
# HELP llamacpp:prompt_tokens_cached_total Total prompt tokens reused from cache
|
||||
# TYPE llamacpp:prompt_tokens_cached_total counter
|
||||
llamacpp:prompt_tokens_cached_total 29650554
|
||||
# HELP llamacpp:prompt_seconds_total Prompt process time
|
||||
# TYPE llamacpp:prompt_seconds_total counter
|
||||
llamacpp:prompt_seconds_total 341.91072852000008
|
||||
# HELP llamacpp:tokens_predicted_total Total tokens generated
|
||||
# TYPE llamacpp:tokens_predicted_total counter
|
||||
llamacpp:tokens_predicted_total 173091
|
||||
# HELP llamacpp:tokens_predicted_seconds_total Predict process time
|
||||
# TYPE llamacpp:tokens_predicted_seconds_total counter
|
||||
llamacpp:tokens_predicted_seconds_total 5458.0845807790029
|
||||
# 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 54515
|
||||
# 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 158803
|
||||
# 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 117552
|
||||
# HELP llamacpp:prompt_tokens_seconds Prompt processing speed in tokens per second
|
||||
# TYPE llamacpp:prompt_tokens_seconds gauge
|
||||
llamacpp:prompt_tokens_seconds 820.2841172907755
|
||||
# HELP llamacpp:predicted_tokens_seconds Generation speed in tokens per second
|
||||
# TYPE llamacpp:predicted_tokens_seconds gauge
|
||||
llamacpp:predicted_tokens_seconds 43.015060732721352
|
||||
# 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
+1
@@ -0,0 +1 @@
|
||||
[{"id":0,"n_ctx":262144,"speculative":true,"is_processing":false,"id_task":-1,"task_id":-1,"state":0,"n_prompt_tokens":0,"n_prompt_tokens_cache":0,"n_prompt_tokens_processed":0,"prompt":"","next_token":[{"has_next_token":false,"has_new_line":false,"n_remain":-1,"n_decoded":0}],"model":"turbo"},{"id":1,"n_ctx":262144,"speculative":true,"is_processing":false,"id_task":-1,"task_id":-1,"state":0,"n_prompt_tokens":0,"n_prompt_tokens_cache":0,"n_prompt_tokens_processed":0,"prompt":"","next_token":[{"has_next_token":false,"has_new_line":false,"n_remain":-1,"n_decoded":0}],"model":"turbo"}]
|
||||
Vendored
+163
@@ -0,0 +1,163 @@
|
||||
# Captured verbatim from http://driveripper.reeselink.com:8000/metrics (vllm-radiance).
|
||||
# Trimmed only by dropping series the dashboard does not read; every kept line is real.
|
||||
process_cpu_seconds_total 240.62
|
||||
# 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"} 2.0
|
||||
# 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: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"} 0.39790575916230364
|
||||
# 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"} 8.582355e+06
|
||||
# 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"} 4.464096e+06
|
||||
# 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:prompt_tokens_total Number of prefill tokens processed.
|
||||
# TYPE vllm:prompt_tokens_total counter
|
||||
vllm:prompt_tokens_total{engine="0",model_name="juggernaut"} 8.582355e+06
|
||||
# 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"} 339918.0
|
||||
vllm:request_success_total{engine="0",finished_reason="stop",model_name="juggernaut"} 2145.0
|
||||
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: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"} 3.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.1",model_name="juggernaut"} 3.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.25",model_name="juggernaut"} 341.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 724.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="0.75",model_name="juggernaut"} 1076.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 1291.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 2114.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 2148.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="7.5",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="80.0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="160.0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="640.0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="2560.0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_count{engine="0",model_name="juggernaut"} 2149.0
|
||||
vllm:time_to_first_token_seconds_sum{engine="0",model_name="juggernaut"} 1861.7778627872467
|
||||
# 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"} 327550.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.075",model_name="juggernaut"} 337018.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.1",model_name="juggernaut"} 337051.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.15",model_name="juggernaut"} 337141.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.2",model_name="juggernaut"} 337229.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.3",model_name="juggernaut"} 337313.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.4",model_name="juggernaut"} 337368.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 337430.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="0.75",model_name="juggernaut"} 337631.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 337651.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="7.5",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="80.0",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_count{engine="0",model_name="juggernaut"} 337769.0
|
||||
vllm:inter_token_latency_seconds_sum{engine="0",model_name="juggernaut"} 12194.350635488052
|
||||
# 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"} 2143.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 2143.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="0.8",model_name="juggernaut"} 2143.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 2143.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="1.5",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="2.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="15.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="30.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="50.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="60.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="120.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="240.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="480.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="960.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="1920.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="7680.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_count{engine="0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_queue_time_seconds_sum{engine="0",model_name="juggernaut"} 2.707464350562077
|
||||
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
|
||||
|
||||
# prefill series (used for the lifetime prompt-speed derivation)
|
||||
# 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"} 20.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="200.0",model_name="juggernaut"} 71.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="500.0",model_name="juggernaut"} 361.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="1000.0",model_name="juggernaut"} 638.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="2000.0",model_name="juggernaut"} 1134.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="5000.0",model_name="juggernaut"} 1943.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="10000.0",model_name="juggernaut"} 2026.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="20000.0",model_name="juggernaut"} 2072.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="50000.0",model_name="juggernaut"} 2112.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="100000.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prompt_tokens_bucket{engine="0",le="+Inf",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prompt_tokens_count{engine="0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prompt_tokens_sum{engine="0",model_name="juggernaut"} 8.441975e+06
|
||||
# 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"} 472.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.5",model_name="juggernaut"} 742.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="0.8",model_name="juggernaut"} 1138.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.0",model_name="juggernaut"} 1318.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="1.5",model_name="juggernaut"} 1976.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.0",model_name="juggernaut"} 2078.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="2.5",model_name="juggernaut"} 2117.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="5.0",model_name="juggernaut"} 2144.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="10.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="15.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="20.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="30.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="40.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="50.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="60.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="120.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="240.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="480.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="960.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="1920.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="7680.0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_bucket{engine="0",le="+Inf",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_count{engine="0",model_name="juggernaut"} 2145.0
|
||||
vllm:request_prefill_time_seconds_sum{engine="0",model_name="juggernaut"} 1796.7229758803733
|
||||
Reference in New Issue
Block a user