Refactor Prometheus and Add Request Level Metrics (#2316)
This commit is contained in:
54
examples/production_monitoring/README.md
Normal file
54
examples/production_monitoring/README.md
Normal file
@@ -0,0 +1,54 @@
|
||||
# vLLM + Prometheus/Grafana
|
||||
|
||||
This is a simple example that shows you how to connect vLLM metric logging to the Prometheus/Grafana stack. For this example, we launch Prometheus and Grafana via Docker. You can checkout other methods through [Prometheus](https://prometheus.io/) and [Grafana](https://grafana.com/) websites.
|
||||
|
||||
Install:
|
||||
- [`docker`](https://docs.docker.com/engine/install/)
|
||||
- [`docker compose`](https://docs.docker.com/compose/install/linux/#install-using-the-repository)
|
||||
|
||||
### Launch
|
||||
|
||||
Prometheus metric logging is enabled by default in the OpenAI-compatible server. Launch via the entrypoint:
|
||||
```bash
|
||||
python3 -m vllm.entrypoints.openai.api_server \
|
||||
--model mistralai/Mistral-7B-v0.1 \
|
||||
--max-model-len 2048 \
|
||||
--disable-log-requests
|
||||
```
|
||||
|
||||
Launch Prometheus and Grafana servers with `docker compose`:
|
||||
```bash
|
||||
docker compose up
|
||||
```
|
||||
|
||||
Submit some sample requests to the server:
|
||||
```bash
|
||||
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
|
||||
|
||||
python3 ../../benchmarks/benchmark_serving.py \
|
||||
--model mistralai/Mistral-7B-v0.1 \
|
||||
--tokenizer mistralai/Mistral-7B-v0.1 \
|
||||
--endpoint /v1/completions \
|
||||
--dataset ShareGPT_V3_unfiltered_cleaned_split.json \
|
||||
--request-rate 3.0
|
||||
```
|
||||
|
||||
Navigating to [`http://localhost:8000/metrics`](http://localhost:8000/metrics) will show the raw Prometheus metrics being exposed by vLLM.
|
||||
|
||||
### Grafana Dashboard
|
||||
|
||||
Navigate to [`http://localhost:3000`](http://localhost:3000). Log in with the default username (`admin`) and password (`admin`).
|
||||
|
||||
#### Add Prometheus Data Source
|
||||
|
||||
Navigate to [`http://localhost:3000/connections/datasources/new`](http://localhost:3000/connections/datasources/new) and select Prometheus.
|
||||
|
||||
On Prometheus configuration page, we need to add the `Prometheus Server URL` in `Connection`. For this setup, Grafana and Prometheus are running in separate containers, but Docker creates DNS name for each containers. You can just use `http://prometheus:9090`.
|
||||
|
||||
Click `Save & Test`. You should get a green check saying "Successfully queried the Prometheus API.".
|
||||
|
||||
#### Import Dashboard
|
||||
|
||||
Navigate to [`http://localhost:3000/dashboard/import`](http://localhost:3000/dashboard/import), upload `grafana.json`, and select the `prometheus` datasource. You should see a screen that looks like the following:
|
||||
|
||||

|
||||
19
examples/production_monitoring/docker-compose.yaml
Normal file
19
examples/production_monitoring/docker-compose.yaml
Normal file
@@ -0,0 +1,19 @@
|
||||
# docker-compose.yaml
|
||||
version: "3"
|
||||
|
||||
services:
|
||||
prometheus:
|
||||
image: prom/prometheus:latest
|
||||
extra_hosts:
|
||||
- "host.docker.internal:host-gateway" # allow a direct connection from container to the local machine
|
||||
ports:
|
||||
- "9090:9090" # the default port used by Prometheus
|
||||
volumes:
|
||||
- ${PWD}/prometheus.yaml:/etc/prometheus/prometheus.yml # mount Prometheus config file
|
||||
|
||||
grafana:
|
||||
image: grafana/grafana:latest
|
||||
depends_on:
|
||||
- prometheus
|
||||
ports:
|
||||
- "3000:3000" # the default port used by Grafana
|
||||
931
examples/production_monitoring/grafana.json
Normal file
931
examples/production_monitoring/grafana.json
Normal file
@@ -0,0 +1,931 @@
|
||||
{
|
||||
"__inputs": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"label": "prometheus",
|
||||
"description": "",
|
||||
"type": "datasource",
|
||||
"pluginId": "prometheus",
|
||||
"pluginName": "Prometheus"
|
||||
}
|
||||
],
|
||||
"__elements": {},
|
||||
"__requires": [
|
||||
{
|
||||
"type": "grafana",
|
||||
"id": "grafana",
|
||||
"name": "Grafana",
|
||||
"version": "10.2.3"
|
||||
},
|
||||
{
|
||||
"type": "datasource",
|
||||
"id": "prometheus",
|
||||
"name": "Prometheus",
|
||||
"version": "1.0.0"
|
||||
},
|
||||
{
|
||||
"type": "panel",
|
||||
"id": "timeseries",
|
||||
"name": "Time series",
|
||||
"version": ""
|
||||
}
|
||||
],
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": {
|
||||
"type": "grafana",
|
||||
"uid": "-- Grafana --"
|
||||
},
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "Monitoring vLLM Inference Server",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 0,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"liveNow": false,
|
||||
"panels": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"description": "End to end request latency measured in seconds.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"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
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 9,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P99",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P95",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P90",
|
||||
"range": true,
|
||||
"refId": "C",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P50",
|
||||
"range": true,
|
||||
"refId": "D",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vllm:e2e_request_latency_seconds_sum[$__rate_interval])\n/\nrate(vllm:e2e_request_latency_seconds_count[$__rate_interval])",
|
||||
"hide": false,
|
||||
"instant": false,
|
||||
"legendFormat": "Average",
|
||||
"range": true,
|
||||
"refId": "E"
|
||||
}
|
||||
],
|
||||
"title": "E2E Request Latency",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"description": "Number of tokens processed per second",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"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": 0
|
||||
},
|
||||
"id": 8,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "rate(vllm:prompt_tokens_total[$__rate_interval])",
|
||||
"fullMetaSearch": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "Prompt Tokens/Sec",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "rate(vllm:generation_tokens_total[$__rate_interval])",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "Generation Tokens/Sec",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"useBackend": false
|
||||
}
|
||||
],
|
||||
"title": "Token Throughput",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"description": "Inter token latency in seconds.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"id": 10,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P99",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P95",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P90",
|
||||
"range": true,
|
||||
"refId": "C",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:time_per_output_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P50",
|
||||
"range": true,
|
||||
"refId": "D",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vllm:time_per_output_token_seconds_sum[$__rate_interval])\n/\nrate(vllm:time_per_output_token_seconds_count[$__rate_interval])",
|
||||
"hide": false,
|
||||
"instant": false,
|
||||
"legendFormat": "Mean",
|
||||
"range": true,
|
||||
"refId": "E"
|
||||
}
|
||||
],
|
||||
"title": "Time Per Output Token Latency",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"description": "Number of requests in RUNNING, WAITING, and SWAPPED state",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "none"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"id": 3,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "vllm:num_requests_running",
|
||||
"fullMetaSearch": false,
|
||||
"includeNullMetadata": true,
|
||||
"instant": false,
|
||||
"legendFormat": "Num Running",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "vllm:num_requests_swapped",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": true,
|
||||
"instant": false,
|
||||
"legendFormat": "Num Swapped",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "vllm:num_requests_waiting",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": true,
|
||||
"instant": false,
|
||||
"legendFormat": "Num Waiting",
|
||||
"range": true,
|
||||
"refId": "C",
|
||||
"useBackend": false
|
||||
}
|
||||
],
|
||||
"title": "Scheduler State",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"description": "P50, P90, P95, and P99 TTFT latency in seconds.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"id": 5,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P99",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.95, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P95",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.9, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P90",
|
||||
"range": true,
|
||||
"refId": "C",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"disableTextWrap": false,
|
||||
"editorMode": "builder",
|
||||
"expr": "histogram_quantile(0.5, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket[$__rate_interval])))",
|
||||
"fullMetaSearch": false,
|
||||
"hide": false,
|
||||
"includeNullMetadata": false,
|
||||
"instant": false,
|
||||
"legendFormat": "P50",
|
||||
"range": true,
|
||||
"refId": "D",
|
||||
"useBackend": false
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "rate(vllm:time_to_first_token_seconds_sum[$__rate_interval])\n/\nrate(vllm:time_to_first_token_seconds_count[$__rate_interval])",
|
||||
"hide": false,
|
||||
"instant": false,
|
||||
"legendFormat": "Average",
|
||||
"range": true,
|
||||
"refId": "E"
|
||||
}
|
||||
],
|
||||
"title": "Time To First Token Latency",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"description": "Percentage of used cache blocks by vLLM.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "percentunit"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"id": 4,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [],
|
||||
"displayMode": "list",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single",
|
||||
"sort": "none"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "vllm:gpu_cache_usage_perc",
|
||||
"instant": false,
|
||||
"legendFormat": "GPU Cache Usage",
|
||||
"range": true,
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "vllm:cpu_cache_usage_perc",
|
||||
"hide": false,
|
||||
"instant": false,
|
||||
"legendFormat": "CPU Cache Usage",
|
||||
"range": true,
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"title": "Cache Utilization",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "",
|
||||
"schemaVersion": 39,
|
||||
"tags": [],
|
||||
"templating": {
|
||||
"list": []
|
||||
},
|
||||
"time": {
|
||||
"from": "now-5m",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "",
|
||||
"title": "vLLM",
|
||||
"uid": "b281712d-8bff-41ef-9f3f-71ad43c05e9b",
|
||||
"version": 2,
|
||||
"weekStart": ""
|
||||
}
|
||||
10
examples/production_monitoring/prometheus.yaml
Normal file
10
examples/production_monitoring/prometheus.yaml
Normal file
@@ -0,0 +1,10 @@
|
||||
# prometheus.yaml
|
||||
global:
|
||||
scrape_interval: 5s
|
||||
evaluation_interval: 30s
|
||||
|
||||
scrape_configs:
|
||||
- job_name: vllm
|
||||
static_configs:
|
||||
- targets:
|
||||
- 'host.docker.internal:8000'
|
||||
Reference in New Issue
Block a user