feat: vLLM Prometheus metrics scraping (#37)

Add ServiceMonitor for llm-serving namespace. Wire prometheus.io annotations to all vLLM pods (reasoning, ornith, embeddings, reranker). Scrape /metrics@8080 every 30s with proper relabeling.
2026-09-11 10:46:15 +09:00
parent 7bd9f83fa7
commit 179e12b9a9
5 changed files with 62 additions and 0 deletions
@@ -104,6 +104,14 @@ spec:
        name: models
      - mountPath: /dev/shm
        name: shm
+    podMetadata:
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+      labels:
+        app.kubernetes.io/name: llm-reasoning
+        app.kubernetes.io/part-of: llm-serving
    deploymentStrategy:
      type: Recreate
    maxReplicas: 1