feat(ai-stack): add DCGM exporter, Prometheus scraper, and Grafana AI Stack intelligence dashboard

manifests/spacedock/ai-stack/ai-stack.yaml

@@ -609,3 +609,53 @@ spec:
       port: 8002
       targetPort: 8002
       nodePort: 30803
+
+---
+# ==============================================================================
+# 4. NVIDIA DCGM EXPORTER (Tesla T4 Telemetry: Utilization, VRAM, Power, Temp)
+# ==============================================================================
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: dcgm-exporter
+  namespace: ai-stack
+  labels:
+    app.kubernetes.io/name: dcgm-exporter
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: dcgm-exporter
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: dcgm-exporter
+    spec:
+      hostNetwork: true
+      containers:
+      - name: dcgm-exporter
+        image: nvcr.io/nvidia/k8s/dcgm-exporter:3.3.8-3.6.0-ubuntu22.04
+        env:
+        - name: DCGM_EXPORTER_LISTEN
+          value: ":9400"
+        - name: DCGM_EXPORTER_KUBERNETES
+          value: "false"
+        - name: LD_LIBRARY_PATH
+          value: "/usr/local/nvidia/lib64"
+        securityContext:
+          privileged: true
+        ports:
+        - name: metrics
+          containerPort: 9400
+        volumeMounts:
+        - name: dev
+          mountPath: /dev
+        - name: nvidia-lib
+          mountPath: /usr/local/nvidia/lib64
+          readOnly: true
+      volumes:
+      - name: dev
+        hostPath:
+          path: /dev
+      - name: nvidia-lib
+        hostPath:
+          path: /usr/local/nvidia/lib64