split off safety so it can be applied one at a time

docs/source/distributions/k8s/vllm-k8s.yaml.template

@@ -32,7 +32,7 @@ spec:
         image: vllm/vllm-openai:latest
         command: ["/bin/sh", "-c"]
         args:
-        - "vllm serve ${INFERENCE_MODEL} --dtype float16 --enforce-eager --max-model-len 6144 --gpu-memory-utilization 0.55"
+        - "vllm serve ${INFERENCE_MODEL} --dtype float16 --enforce-eager --max-model-len 4096 --gpu-memory-utilization 0.5"
         env:
         - name: HUGGING_FACE_HUB_TOKEN
           valueFrom:
@@ -48,66 +48,3 @@ spec:
       - name: llama-storage
         persistentVolumeClaim:
           claimName: vllm-models
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: vllm-server
-spec:
-  selector:
-    app.kubernetes.io/name: vllm
-  ports:
-  - protocol: TCP
-    port: 8000
-    targetPort: 8000
-  type: ClusterIP
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: vllm-server-safety
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: vllm-safety
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: vllm-safety
-    spec:
-      containers:
-      - name: vllm-safety
-        image: vllm/vllm-openai:latest
-        command: ["/bin/sh", "-c"]
-        args: [
-          "vllm serve ${SAFETY_MODEL} --dtype float16 --enforce-eager --max-model-len 6144 --gpu-memory-utilization 0.28"
-        ]
-        env:
-        - name: HUGGING_FACE_HUB_TOKEN
-          valueFrom:
-            secretKeyRef:
-              name: hf-token-secret
-              key: token
-        ports:
-          - containerPort: 8001
-        volumeMounts:
-          - name: llama-storage
-            mountPath: /root/.cache/huggingface
-      volumes:
-      - name: llama-storage
-        persistentVolumeClaim:
-          claimName: vllm-models
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: vllm-server-safety
-spec:
-  selector:
-    app.kubernetes.io/name: vllm-safety
-  ports:
-  - protocol: TCP
-    port: 8001
-    targetPort: 8001
-  type: ClusterIP