Upload k8s.yaml

Add HPA, probes, and preprocessor microservice

k8s.yaml

@@ -3,7 +3,7 @@ kind: Deployment
 metadata:
   name: triton-deployment
 spec:
-  replicas: 1
+  replicas: 2
   selector:
     matchLabels:
       app: triton
@@ -17,16 +17,43 @@ spec:
     spec:
       containers:
       - name: triton
-        image: nvcr.io/nvidia/tritonserver:22.10-py3
-        args: ["tritonserver", "--model-repository=/models"]
+        image: nvcr.io/nvidia/tritonserver:23.01-py3
+        args: ["tritonserver","--model-repository=/models","--http-port=8000","--grpc-port=8001","--metrics-port=8002"]
         ports:
-        - containerPort: 8000
-        - containerPort: 8001
-        - containerPort: 8002
+        - {containerPort: 8000, name: http}
+        - {containerPort: 8001, name: grpc}
+        - {containerPort: 8002, name: metrics}
+        resources:
+          requests: { cpu: "500m", memory: "1Gi" }
+          limits:   { cpu: "2",    memory: "4Gi" }
         volumeMounts:
         - name: model-volume
           mountPath: /models
+        readinessProbe:
+          httpGet: { path: /v2/health/ready, port: 8000 }
+          initialDelaySeconds: 10
+          periodSeconds: 5
+        livenessProbe:
+          httpGet: { path: /v2/health/live, port: 8000 }
+          initialDelaySeconds: 20
+          periodSeconds: 10
       volumes:
       - name: model-volume
         persistentVolumeClaim:
           claimName: model-pvc
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: triton-service
+spec:
+  selector:
+    app: triton
+  ports:
+    - name: http
+      port: 8000
+      targetPort: 8000
+    - name: grpc
+      port: 8001
+      targetPort: 8001
+  type: ClusterIP