Pod -> Deployment, NodePort -> ClusterIP

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>

docs/source/distributions/kubernetes_deployment.md

@@ -32,13 +32,20 @@ type: Opaque
 data:
   token: "<YOUR-HF-TOKEN>"
 ---
-apiVersion: v1
-kind: Pod
+apiVersion: apps/v1
+kind: Deployment
 metadata:
   name: vllm-server
-  labels:
-    app: vllm
 spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: vllm
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: vllm
+    spec:
       containers:
       - name: llama-stack
         image: <VLLM-IMAGE>
@@ -73,11 +80,12 @@ metadata:
   name: vllm-server
 spec:
   selector:
-    app: vllm
+    app.kubernetes.io/name: vllm
   ports:
-  - port: 8000
+  - protocol: TCP
+    port: 8000
     targetPort: 8000
-  type: NodePort
+  type: ClusterIP
 EOF
 ```
 
@@ -135,13 +143,20 @@ spec:
     requests:
       storage: 1Gi
 ---
-apiVersion: v1
-kind: Pod
+apiVersion: apps/v1
+kind: Deployment
 metadata:
-  name: llama-stack-pod
-  labels:
-    app: llama-stack
+  name: llama-stack-server
 spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: llama-stack
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: llama-stack
+    spec:
       containers:
       - name: llama-stack
         image: localhost/llama-stack-run-k8s:latest
@@ -163,7 +178,7 @@ metadata:
   name: llama-stack-service
 spec:
   selector:
-    app: llama-stack
+    app.kubernetes.io/name: llama-stack
   ports:
   - protocol: TCP
     port: 5000