Unverified Commit 5bc2508b authored by Yudi Xue's avatar Yudi Xue Committed by GitHub
Browse files

Monitoring documentation (#1933)

parent a71a44f2
# Production Metrics
sglang exposes the following metrics via Prometheus. The metrics are namespaced by `$name` (the model name).
An example of the monitoring dashboard is available in [examples/monitoring/grafana.json](../examples/monitoring/grafana.json).
Here is an example of the metrics:
```
# HELP sglang:max_total_num_tokens Maximum total number of tokens
# TYPE sglang:max_total_num_tokens gauge
sglang:max_total_num_tokens{name="google/gemma-2-9b-it"} 161721.0
# HELP sglang:max_prefill_tokens Maximum prefill tokens
# TYPE sglang:max_prefill_tokens gauge
sglang:max_prefill_tokens{name="google/gemma-2-9b-it"} 16384.0
# HELP sglang:max_running_requests Maximum running requests
# TYPE sglang:max_running_requests gauge
sglang:max_running_requests{name="google/gemma-2-9b-it"} 4097.0
# HELP sglang:context_len Context length
# TYPE sglang:context_len gauge
sglang:context_len{name="google/gemma-2-9b-it"} 8192.0
# HELP sglang:prompt_tokens_total Number of prefill tokens processed.
# TYPE sglang:prompt_tokens_total counter
sglang:prompt_tokens_total{name="google/gemma-2-9b-it"} 506780.0
# HELP sglang:generation_tokens_total Number of generation tokens processed.
# TYPE sglang:generation_tokens_total counter
sglang:generation_tokens_total{name="google/gemma-2-9b-it"} 424549.0
# HELP sglang:num_requests_running Number of requests currently running on GPU
# TYPE sglang:num_requests_running gauge
sglang:num_requests_running{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:num_requests_waiting Number of requests waiting to be processed.
# TYPE sglang:num_requests_waiting gauge
sglang:num_requests_waiting{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:gen_throughput Gen token throughput (token/s)
# TYPE sglang:gen_throughput gauge
sglang:gen_throughput{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:token_usage Total token usage
# TYPE sglang:token_usage gauge
sglang:token_usage{name="google/gemma-2-9b-it"} 0.01
# HELP sglang:new_seq Number of new sequences
# TYPE sglang:new_seq gauge
sglang:new_seq{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:new_token Number of new token
# TYPE sglang:new_token gauge
sglang:new_token{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:cached_token Number of cached token
# TYPE sglang:cached_token gauge
sglang:cached_token{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:cache_hit_rate Cache hit rate
# TYPE sglang:cache_hit_rate gauge
sglang:cache_hit_rate{name="google/gemma-2-9b-it"} 10.61
# HELP sglang:queue_req Number of queued requests
# TYPE sglang:queue_req gauge
sglang:queue_req{name="google/gemma-2-9b-it"} 0.0
# HELP sglang:time_to_first_token_seconds Histogram of time to first token in seconds.
# TYPE sglang:time_to_first_token_seconds histogram
sglang:time_to_first_token_seconds_sum{name="google/gemma-2-9b-it"} 656.0780844688416
sglang:time_to_first_token_seconds_bucket{le="0.001",name="google/gemma-2-9b-it"} 0.0
sglang:time_to_first_token_seconds_bucket{le="0.005",name="google/gemma-2-9b-it"} 0.0
sglang:time_to_first_token_seconds_bucket{le="0.01",name="google/gemma-2-9b-it"} 0.0
sglang:time_to_first_token_seconds_bucket{le="0.02",name="google/gemma-2-9b-it"} 0.0
sglang:time_to_first_token_seconds_bucket{le="0.04",name="google/gemma-2-9b-it"} 207.0
sglang:time_to_first_token_seconds_bucket{le="0.06",name="google/gemma-2-9b-it"} 456.0
sglang:time_to_first_token_seconds_bucket{le="0.08",name="google/gemma-2-9b-it"} 598.0
sglang:time_to_first_token_seconds_bucket{le="0.1",name="google/gemma-2-9b-it"} 707.0
sglang:time_to_first_token_seconds_bucket{le="0.25",name="google/gemma-2-9b-it"} 1187.0
sglang:time_to_first_token_seconds_bucket{le="0.5",name="google/gemma-2-9b-it"} 1350.0
sglang:time_to_first_token_seconds_bucket{le="0.75",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="1.0",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="2.5",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="5.0",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="7.5",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="10.0",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="15.0",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="20.0",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="25.0",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="30.0",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_bucket{le="+Inf",name="google/gemma-2-9b-it"} 2124.0
sglang:time_to_first_token_seconds_count{name="google/gemma-2-9b-it"} 2124.0
# HELP sglang:time_per_output_token_seconds Histogram of time per output token in seconds.
# TYPE sglang:time_per_output_token_seconds histogram
sglang:time_per_output_token_seconds_sum{name="google/gemma-2-9b-it"} 29846.5393948555
sglang:time_per_output_token_seconds_bucket{le="0.005",name="google/gemma-2-9b-it"} 0.0
sglang:time_per_output_token_seconds_bucket{le="0.01",name="google/gemma-2-9b-it"} 0.0
sglang:time_per_output_token_seconds_bucket{le="0.015",name="google/gemma-2-9b-it"} 0.0
sglang:time_per_output_token_seconds_bucket{le="0.02",name="google/gemma-2-9b-it"} 9602.0
sglang:time_per_output_token_seconds_bucket{le="0.025",name="google/gemma-2-9b-it"} 30060.0
sglang:time_per_output_token_seconds_bucket{le="0.03",name="google/gemma-2-9b-it"} 39184.0
sglang:time_per_output_token_seconds_bucket{le="0.04",name="google/gemma-2-9b-it"} 61387.0
sglang:time_per_output_token_seconds_bucket{le="0.05",name="google/gemma-2-9b-it"} 78835.0
sglang:time_per_output_token_seconds_bucket{le="0.075",name="google/gemma-2-9b-it"} 139394.0
sglang:time_per_output_token_seconds_bucket{le="0.1",name="google/gemma-2-9b-it"} 422029.0
sglang:time_per_output_token_seconds_bucket{le="0.15",name="google/gemma-2-9b-it"} 422029.0
sglang:time_per_output_token_seconds_bucket{le="0.2",name="google/gemma-2-9b-it"} 422029.0
sglang:time_per_output_token_seconds_bucket{le="0.3",name="google/gemma-2-9b-it"} 422424.0
sglang:time_per_output_token_seconds_bucket{le="0.4",name="google/gemma-2-9b-it"} 422424.0
sglang:time_per_output_token_seconds_bucket{le="0.5",name="google/gemma-2-9b-it"} 422425.0
sglang:time_per_output_token_seconds_bucket{le="0.75",name="google/gemma-2-9b-it"} 422425.0
sglang:time_per_output_token_seconds_bucket{le="1.0",name="google/gemma-2-9b-it"} 422425.0
sglang:time_per_output_token_seconds_bucket{le="2.5",name="google/gemma-2-9b-it"} 422425.0
sglang:time_per_output_token_seconds_bucket{le="+Inf",name="google/gemma-2-9b-it"} 422425.0
sglang:time_per_output_token_seconds_count{name="google/gemma-2-9b-it"} 422425.0
# HELP sglang:request_prompt_tokens Number of prefill tokens processed
# TYPE sglang:request_prompt_tokens histogram
sglang:request_prompt_tokens_sum{name="google/gemma-2-9b-it"} 500552.0
sglang:request_prompt_tokens_bucket{le="1.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_prompt_tokens_bucket{le="2.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_prompt_tokens_bucket{le="5.0",name="google/gemma-2-9b-it"} 22.0
sglang:request_prompt_tokens_bucket{le="10.0",name="google/gemma-2-9b-it"} 191.0
sglang:request_prompt_tokens_bucket{le="20.0",name="google/gemma-2-9b-it"} 511.0
sglang:request_prompt_tokens_bucket{le="50.0",name="google/gemma-2-9b-it"} 825.0
sglang:request_prompt_tokens_bucket{le="100.0",name="google/gemma-2-9b-it"} 997.0
sglang:request_prompt_tokens_bucket{le="200.0",name="google/gemma-2-9b-it"} 1182.0
sglang:request_prompt_tokens_bucket{le="500.0",name="google/gemma-2-9b-it"} 1748.0
sglang:request_prompt_tokens_bucket{le="1000.0",name="google/gemma-2-9b-it"} 2102.0
sglang:request_prompt_tokens_bucket{le="2000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_prompt_tokens_bucket{le="5000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_prompt_tokens_bucket{le="10000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_prompt_tokens_bucket{le="20000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_prompt_tokens_bucket{le="50000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_prompt_tokens_bucket{le="100000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_prompt_tokens_bucket{le="+Inf",name="google/gemma-2-9b-it"} 2104.0
sglang:request_prompt_tokens_count{name="google/gemma-2-9b-it"} 2104.0
# HELP sglang:request_generation_tokens Number of generation tokens processed.
# TYPE sglang:request_generation_tokens histogram
sglang:request_generation_tokens_sum{name="google/gemma-2-9b-it"} 424529.0
sglang:request_generation_tokens_bucket{le="1.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_generation_tokens_bucket{le="2.0",name="google/gemma-2-9b-it"} 0.0
sglang:request_generation_tokens_bucket{le="5.0",name="google/gemma-2-9b-it"} 49.0
sglang:request_generation_tokens_bucket{le="10.0",name="google/gemma-2-9b-it"} 202.0
sglang:request_generation_tokens_bucket{le="20.0",name="google/gemma-2-9b-it"} 448.0
sglang:request_generation_tokens_bucket{le="50.0",name="google/gemma-2-9b-it"} 814.0
sglang:request_generation_tokens_bucket{le="100.0",name="google/gemma-2-9b-it"} 979.0
sglang:request_generation_tokens_bucket{le="200.0",name="google/gemma-2-9b-it"} 1266.0
sglang:request_generation_tokens_bucket{le="500.0",name="google/gemma-2-9b-it"} 1883.0
sglang:request_generation_tokens_bucket{le="1000.0",name="google/gemma-2-9b-it"} 2095.0
sglang:request_generation_tokens_bucket{le="2000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_generation_tokens_bucket{le="5000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_generation_tokens_bucket{le="10000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_generation_tokens_bucket{le="20000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_generation_tokens_bucket{le="50000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_generation_tokens_bucket{le="100000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:request_generation_tokens_bucket{le="+Inf",name="google/gemma-2-9b-it"} 2104.0
sglang:request_generation_tokens_count{name="google/gemma-2-9b-it"} 2104.0
# HELP sglang:e2e_request_latency_seconds Histogram of End-to-end request latency in seconds
# TYPE sglang:e2e_request_latency_seconds histogram
sglang:e2e_request_latency_seconds_sum{name="google/gemma-2-9b-it"} 70517.99934530258
sglang:e2e_request_latency_seconds_bucket{le="1.0",name="google/gemma-2-9b-it"} 2.0
sglang:e2e_request_latency_seconds_bucket{le="2.0",name="google/gemma-2-9b-it"} 21.0
sglang:e2e_request_latency_seconds_bucket{le="5.0",name="google/gemma-2-9b-it"} 54.0
sglang:e2e_request_latency_seconds_bucket{le="10.0",name="google/gemma-2-9b-it"} 311.0
sglang:e2e_request_latency_seconds_bucket{le="20.0",name="google/gemma-2-9b-it"} 733.0
sglang:e2e_request_latency_seconds_bucket{le="50.0",name="google/gemma-2-9b-it"} 1563.0
sglang:e2e_request_latency_seconds_bucket{le="100.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="200.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="500.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="1000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="2000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="5000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="10000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="20000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="50000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="100000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_bucket{le="+Inf",name="google/gemma-2-9b-it"} 2104.0
sglang:e2e_request_latency_seconds_count{name="google/gemma-2-9b-it"} 2104.0
# HELP sglang:waiting_request_latency_seconds Histogram of request waiting time in seconds
# TYPE sglang:waiting_request_latency_seconds histogram
sglang:waiting_request_latency_seconds_sum{name="google/gemma-2-9b-it"} 24885.007263183594
sglang:waiting_request_latency_seconds_bucket{le="1.0",name="google/gemma-2-9b-it"} 421.0
sglang:waiting_request_latency_seconds_bucket{le="2.0",name="google/gemma-2-9b-it"} 563.0
sglang:waiting_request_latency_seconds_bucket{le="5.0",name="google/gemma-2-9b-it"} 900.0
sglang:waiting_request_latency_seconds_bucket{le="10.0",name="google/gemma-2-9b-it"} 1270.0
sglang:waiting_request_latency_seconds_bucket{le="20.0",name="google/gemma-2-9b-it"} 1623.0
sglang:waiting_request_latency_seconds_bucket{le="50.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="100.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="200.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="500.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="1000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="2000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="5000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="10000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="20000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="50000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="100000.0",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_bucket{le="+Inf",name="google/gemma-2-9b-it"} 2104.0
sglang:waiting_request_latency_seconds_count{name="google/gemma-2-9b-it"} 2104.0
```
## Setup Guide
To setup a monitoring dashboard, you can use the following docker compose file: [examples/monitoring/docker-compose.yaml](../examples/monitoring/docker-compose.yaml).
Assume you have sglang server running at `localhost:30000`.
To start the monitoring dashboard (prometheus + grafana), cd to `examples/monitoring` and run:
```bash
docker compose -f compose.yaml -p monitoring up
```
Then you can access the Grafana dashboard at http://localhost:3000.
### Grafana Dashboard
To import the Grafana dashboard, click `+` -> `Import` -> `Upload JSON file` -> `Upload` and select [grafana.json](../examples/monitoring/grafana.json).
services:
prometheus:
image: prom/prometheus:latest
network_mode: host
ports:
- "9090:9090"
volumes:
- ${PWD}/prometheus.yaml:/etc/prometheus/prometheus.yml
grafana:
image: grafana/grafana:latest
network_mode: host
depends_on:
- prometheus
ports:
- "3000:3000"
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 1,
"links": [],
"panels": [
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"description": "max-running-requests from server argument",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 3,
"x": 0,
"y": 0
},
"id": 2,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"last"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sglang:max_running_requests{name=\"$name\", instance=\"$instance\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Max Running Requests",
"type": "stat"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"description": "Supported context length with loaded model",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 3,
"x": 3,
"y": 0
},
"id": 1,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"last"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sglang:context_len{instance=\"$instance\", name=\"$name\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Max Context Length",
"type": "stat"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"description": "max_total_tokens",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 3,
"x": 6,
"y": 0
},
"id": 4,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"last"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sglang:max_total_num_tokens{instance=\"$instance\", name=\"$name\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Max Total Num Tokens",
"type": "stat"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"description": "max_prefill_tokens from server args",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 3,
"x": 9,
"y": 0
},
"id": 3,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"last"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sglang:max_prefill_tokens{instance=\"$instance\", name=\"$name\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Max Prefill Tokens",
"type": "stat"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 6,
"x": 12,
"y": 0
},
"id": 6,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sglang:cached_token{instance=\"$instance\", name=\"$name\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Cached Tokens",
"type": "stat"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 6,
"x": 18,
"y": 0
},
"id": 5,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sglang:cache_hit_rate{instance=\"$instance\", name=\"$name\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Cache Hit Rate (%)",
"type": "stat"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 3
},
"id": 14,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P99",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "histogram_quantile(0.9, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P90",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.95, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$model_name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P95",
"range": true,
"refId": "C",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "histogram_quantile(0.5, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$model_name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P50",
"range": true,
"refId": "D",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "rate(sglang:e2e_request_latency_seconds_sum{instance=\"$instance\", name=\"$model_name\"}[$__rate_interval]) / rate(sglang:e2e_request_latency_seconds_count[$__rate_interval])",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Average",
"range": true,
"refId": "E",
"useBackend": false
}
],
"title": "E2E Request Latency (S)",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 3
},
"id": 18,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"editorMode": "code",
"expr": "sglang:gen_throughput{instance=\"$instance\", name=\"$name\"}",
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A"
}
],
"title": "Generation Throughput (Token / S)",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 11
},
"id": 7,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sglang:num_requests_running{instance=\"$instance\", name=\"$name\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Num Requests Running",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 11
},
"id": 8,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sglang:num_requests_waiting{instance=\"$instance\", name=\"$name\"}",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Number of Requests Waiting",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 19
},
"id": 16,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P99",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "histogram_quantile(0.9, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P90",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "histogram_quantile(0.95, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P95",
"range": true,
"refId": "C",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "histogram_quantile(0.5, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "P50",
"range": true,
"refId": "D",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "rate(sglang:e2e_request_latency_seconds_sum{name=\"$name\"}[$__rate_interval]) / rate(sglang:e2e_request_latency_seconds_count{name=\"$name\"}[$__rate_interval])",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Average",
"range": true,
"refId": "E",
"useBackend": false
}
],
"title": "Time Request Decoding (S)",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"description": "Time requests waiting before added to batch",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 19
},
"id": 15,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"instant": false,
"legendFormat": "P99",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"editorMode": "code",
"expr": "histogram_quantile(0.95, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"hide": false,
"instant": false,
"legendFormat": "P95",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"editorMode": "code",
"expr": "histogram_quantile(0.9, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"hide": false,
"instant": false,
"legendFormat": "P90",
"range": true,
"refId": "C"
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"editorMode": "code",
"expr": "histogram_quantile(0.5, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))",
"hide": false,
"instant": false,
"legendFormat": "P50",
"range": true,
"refId": "D"
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"editorMode": "code",
"expr": "rate(sglang:waiting_request_latency_seconds_sum{name=\"$name\"}[$__rate_interval])\r\n/\r\nrate(sglang:waiting_request_latency_seconds_count{name=\"$name\"}[$__rate_interval])",
"hide": false,
"instant": false,
"legendFormat": "Average",
"range": true,
"refId": "E"
}
],
"title": "Time Request Waiting (S)",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 27
},
"id": 11,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(rate(sglang:request_prompt_tokens_sum{instance=\"$instance\", name=\"$name\"}[$__rate_interval])) by (instance, name)",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "B",
"useBackend": false
}
],
"title": "Prompt Tokens",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 27
},
"id": 17,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum(rate(sglang:request_generation_tokens_sum{instance=\"$instance\", name=\"$name\"}[$__rate_interval])) by (instance, name)",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Generated Tokens",
"type": "timeseries"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"fieldConfig": {
"defaults": {
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"scaleDistribution": {
"type": "linear"
}
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 35
},
"id": 13,
"options": {
"calculate": false,
"calculation": {
"yBuckets": {
"scale": {
"log": 2,
"type": "log"
}
}
},
"cellGap": 1,
"color": {
"exponent": 0.5,
"fill": "dark-orange",
"mode": "scheme",
"reverse": false,
"scale": "exponential",
"scheme": "Oranges",
"steps": 64
},
"exemplars": {
"color": "rgba(255,0,255,0.7)"
},
"filterValues": {
"le": 1e-9
},
"legend": {
"show": true
},
"rowsFrame": {
"layout": "auto"
},
"tooltip": {
"mode": "single",
"showColorScale": false,
"yHistogram": false
},
"yAxis": {
"axisPlacement": "left",
"reverse": false
}
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(le) (increase(sglang:request_prompt_tokens_bucket{name=\"$name\", instance=\"$instance\"}[$__rate_interval]))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Request Prompt Tokens",
"type": "heatmap"
},
{
"datasource": {
"default": true,
"type": "prometheus",
"uid": "ee2vha8w6f5kwf"
},
"description": "",
"fieldConfig": {
"defaults": {
"custom": {
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"scaleDistribution": {
"type": "linear"
}
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 35
},
"id": 12,
"options": {
"calculate": false,
"calculation": {
"xBuckets": {
"mode": "size",
"value": ""
},
"yBuckets": {
"mode": "size",
"scale": {
"log": 2,
"type": "log"
},
"value": ""
}
},
"cellGap": 1,
"color": {
"exponent": 0.5,
"fill": "dark-orange",
"min": 0,
"mode": "scheme",
"reverse": false,
"scale": "exponential",
"scheme": "Spectral",
"steps": 64
},
"exemplars": {
"color": "rgba(255,0,255,0.7)"
},
"filterValues": {
"le": 1e-9
},
"legend": {
"show": true
},
"rowsFrame": {
"layout": "auto",
"value": "Request count"
},
"tooltip": {
"mode": "single",
"showColorScale": false,
"yHistogram": true
},
"yAxis": {
"axisLabel": "Generation Length",
"axisPlacement": "left",
"reverse": false,
"unit": "none"
}
},
"pluginVersion": "11.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "sum by(le) (increase(sglang:request_generation_tokens_bucket{name=\"$name\", instance=\"$instance\"}[$__rate_interval]))",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{__name__}}",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "Request Generation Tokens",
"type": "heatmap"
}
],
"refresh": "5s",
"schemaVersion": 39,
"tags": [],
"templating": {
"list": [
{
"current": {
"selected": false,
"text": "127.0.0.1:30000",
"value": "127.0.0.1:30000"
},
"datasource": {
"type": "prometheus",
"uid": "ddyfngn31dg5cf"
},
"definition": "label_values(instance)",
"hide": 0,
"includeAll": false,
"label": "instance",
"multi": false,
"name": "instance",
"options": [],
"query": {
"qryType": 1,
"query": "label_values(instance)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
},
{
"current": {
"selected": true,
"text": "google/gemma-2-9b-it",
"value": "google/gemma-2-9b-it"
},
"definition": "label_values(name)",
"hide": 1,
"includeAll": false,
"label": "name",
"multi": false,
"name": "name",
"options": [],
"query": {
"qryType": 1,
"query": "label_values(name)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
}
]
},
"time": {
"from": "now-30m",
"to": "now"
},
"timepicker": {},
"timezone": "browser",
"title": "SGLang Dashboard",
"uid": "ddyp55uq7brpcc",
"version": 3,
"weekStart": ""
}
# prometheus.yaml
global:
scrape_interval: 5s
evaluation_interval: 30s
scrape_configs:
- job_name: sglang
static_configs:
- targets:
- '127.0.0.1:30000'
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment