Admin Bot
44ec3502dc
- RecordTTFT: Time-to-First-Token in milliseconds - RecordITL: Inter-Token Latency in milliseconds - RecordTokenCount: Track total tokens generated - Prometheus exporter for /metrics endpoint - Grafana dashboard ConfigMap (llm-metrics.json) - ResponseWriterWrapper to capture metrics during LLM calls - Metrics exported: llm_ttft_seconds, llm_itl_seconds, llm_tokens_total
322 lines
8.1 KiB
YAML
322 lines
8.1 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-llm-metrics
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
data:
|
|
llm-metrics.json: |
|
|
{
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"builtIn": 1,
|
|
"datasource": "-- Grafana --",
|
|
"enable": true,
|
|
"hide": true,
|
|
"iconColor": "rgba(0, 211, 255, 1)",
|
|
"name": "Annotations & Alerts",
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"editable": true,
|
|
"gnetId": null,
|
|
"graphTooltip": 0,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisLabel": "Milliseconds",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": 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": 0
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"min"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "bottom"
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi"
|
|
}
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llm_ttft_seconds * 1000",
|
|
"legendFormat": "{{model}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Time to First Token (TTFT) by Model",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisLabel": "Milliseconds",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": 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": 0
|
|
},
|
|
"id": 3,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"min"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "bottom"
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi"
|
|
}
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llm_itl_seconds * 1000",
|
|
"legendFormat": "{{model}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Inter-Token Latency (ITL) by Model",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"hideFrom": {
|
|
"tooltip": false,
|
|
"viz": false,
|
|
"legend": false
|
|
}
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"id": 4,
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom"
|
|
},
|
|
"pieType": "pie"
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "llm_tokens_total",
|
|
"legendFormat": "{{model}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Total Tokens Generated by Model",
|
|
"type": "piechart"
|
|
},
|
|
{
|
|
"datasource": "Prometheus",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 50
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 100
|
|
}
|
|
]
|
|
},
|
|
"unit": "ms"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"id": 5,
|
|
"options": {
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"values": false,
|
|
"fields": "",
|
|
"calcs": [
|
|
"lastNotNull"
|
|
]
|
|
},
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true
|
|
},
|
|
"pluginVersion": "8.0.0",
|
|
"targets": [
|
|
{
|
|
"expr": "avg(llm_ttft_seconds) * 1000",
|
|
"legendFormat": "Average TTFT",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Average TTFT (All Models)",
|
|
"type": "gauge"
|
|
}
|
|
],
|
|
"refresh": "10s",
|
|
"schemaVersion": 27,
|
|
"style": "dark",
|
|
"tags": [
|
|
"llm",
|
|
"inference",
|
|
"metrics"
|
|
],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "",
|
|
"title": "LLM Inference Metrics (TTFT & ITL)",
|
|
"uid": "llm-metrics",
|
|
"version": 0
|
|
}
|