Merge branch 'feature/37-vllm-prometheus-scraping'

k8s/apps/llm-serving/embeddings.yaml

@@ -45,6 +45,14 @@ spec:
       volumeMounts:
       - mountPath: /mnt/models
         name: models
+    podMetadata:
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+      labels:
+        app.kubernetes.io/name: llm-embeddings
+        app.kubernetes.io/part-of: llm-serving
     maxReplicas: 1
     minReplicas: 1
     nodeSelector:

k8s/apps/llm-serving/ornith.yaml

@@ -83,6 +83,14 @@ spec:
       volumeMounts:
       - mountPath: /mnt/models
         name: models
+    podMetadata:
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+      labels:
+        app.kubernetes.io/name: llm-ornith
+        app.kubernetes.io/part-of: llm-serving
     deploymentStrategy:
       type: Recreate
     # 1 replica -- ornith:35b only. qwen2.5:3b moved to CPU on cp-2.

k8s/apps/llm-serving/reasoning.yaml

@@ -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

k8s/apps/llm-serving/reranker.yaml

@@ -45,6 +45,14 @@ spec:
       volumeMounts:
       - mountPath: /mnt/models
         name: models
+    podMetadata:
+      annotations:
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "8080"
+        prometheus.io/path: "/metrics"
+      labels:
+        app.kubernetes.io/name: llm-reranker
+        app.kubernetes.io/part-of: llm-serving
     maxReplicas: 1
     minReplicas: 1
     nodeSelector:

k8s/infra/monitoring/servicemonitors/vllm.yaml

@@ -0,0 +1,30 @@
+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:
+    matchLabels:
+      app.kubernetes.io/part-of: llm-serving
+  endpoints:
+    - port: http
+      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