integrations/vllm/documentation.yaml

exporter_type: included
app_name_short: vLLM
app_name: {{app_name_short}}
app_site_name: {{app_name_short}}
app_site_url: https://docs.vllm.ai/en/latest/
exporter_name: the {{app_name_short}} exporter
exporter_repo_url: https://docs.vllm.ai/en/stable/serving/metrics.html
gke_setup_url: /kubernetes-engine/docs/tutorials/serve-gemma-gpu-vllm
additional_prereq_info: |
  {{app_site_name}} exposes Prometheus-format metrics automatically; you do not
  have to install it separately. To verify that {{exporter_name}} is emitting
  metrics on the expected endpoints, do the following:

  1. Set up port forwarding by using the following command:

  <pre class="devsite-click-to-copy">
  kubectl -n {{namespace_name}} port-forward {{pod_name}} 8000
  </pre>

  2. Access the endpoint `localhost:8000/metrics` by using the browser
  or the `curl` utility in another terminal session.
dashboard_available: true
multiple_dashboards: false
dashboard_display_name: {{app_name_short}} Prometheus Overview
podmonitoring_config: |
  apiVersion: monitoring.googleapis.com/v1
  kind: PodMonitoring
  metadata:
    name: vllm
    labels:
      app.kubernetes.io/name: vllm
      app.kubernetes.io/part-of: google-cloud-managed-prometheus
  spec:
    endpoints:
    - port: 8000
      scheme: http
      interval: 30s
      path: /metrics
    selector:
      matchLabels:
        app: vllm-gemma-server
additional_podmonitoring_info: |
  Ensure that the values of the `port` and `matchLabels` fields match those of the {{app_name_short}} pods you want to monitor.
sample_promql_query: up{job="vllm", cluster="{{cluster_name}}", namespace="{{namespace_name}}"}