homelab/k8s/infra/monitoring/servicemonitors/vllm.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: vllm
  namespace: monitoring
  labels:
    app.kubernetes.io/name: vllm
    app.kubernetes.io/part-of: llm-serving
spec:
  namespaceSelector:
    matchNames:
      - llm-serving
  selector:
    # Only the three engines that actually serve /metrics.
    # ornith-predictor and qwen-cpu are Ollama, which has no Prometheus
    # endpoint (/metrics returns 404) — selecting them would add permanently
    # DOWN targets. Ollama-model visibility comes from the api-gateway
    # ServiceMonitor instead (llm_ttft_seconds / llm_itl_seconds are
    # measured at the proxy, so they cover every model including Ollama).
    matchExpressions:
      - key: app.kubernetes.io/name
        operator: In
        values:
          - llm-reasoning   # vLLM 0.11.0 — full engine metrics
          - llm-embeddings  # TEI 1.8.2 — CPU
          - llm-reranker    # TEI 1.8.2 — CPU
  endpoints:
    # targetPort, not port: the KServe-generated Services on llm-serving have
    # UNNAMED ports, so `port: <name>` can never match. Naming them would mean
    # editing the InferenceServices (predictor restart = full weights reload,
    # tens of seconds on the vLLM slot), so scrape the pod port directly.
    # prometheus-operator v0.94.1 supports targetPort on ServiceMonitor.
    - targetPort: 8080
      interval: 30s
      scrapeTimeout: 10s
      path: /metrics
      scheme: http
      relabelings:
        - sourceLabels: [__meta_kubernetes_namespace]
          targetLabel: namespace
        - sourceLabels: [__meta_kubernetes_pod_name]
          targetLabel: pod
        - sourceLabels: [__meta_kubernetes_service_name]
          targetLabel: service
        - sourceLabels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
          targetLabel: app