docker run -d --name vllm-cpu \
  -p 8000:8000 \
  -e MODEL_NAME=meta-llama/Llama-3.2-1B-Instruct \
  docker.io/vllm/vllm-openai-cpu:latest

docker run -d --name vllm-cpu \
  --restart unless-stopped \
  -p 8000:8000 \
  -v /data/models:/models \
  -e MODEL_NAME=/models/llama-3.2-1b \
  -e MAX_MODEL_LEN=4096 \
  docker.io/vllm/vllm-openai-cpu:v0.6.0

apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-cpu
spec:
  replicas: 1
  selector:
    matchLabels:
      app: vllm-cpu
  template:
    metadata:
      labels:
        app: vllm-cpu
    spec:
      containers:
        - name: vllm
          image: docker.io/vllm/vllm-openai-cpu:v0.6.0
          ports:
            - containerPort: 8000
          env:
            - name: MODEL_NAME
              value: /models/llama-3.2-1b
          resources:
            requests:
              memory: 8Gi
          volumeMounts:
            - name: models
              mountPath: /models
      volumes:
        - name: models
          persistentVolumeClaim:
            claimName: llm-models
---
apiVersion: v1
kind: Service
metadata:
  name: vllm-cpu
spec:
  selector:
    app: vllm-cpu
  ports:
    - port: 8000
      targetPort: 8000