cpu-deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-llama2-7b-pool
spec:
  replicas: 3
  selector:
    matchLabels:
      app: vllm-llama2-7b-pool
  template:
    metadata:
      labels:
        app: vllm-llama2-7b-pool
    spec:
      containers:
        - name: lora
          image: "seedjeffwan/vllm-cpu-env:bb392af4-20250203"
          imagePullPolicy: Always
          command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
          args:
          - "--model"
          - "Qwen/Qwen2.5-1.5B-Instruct"
          - "--port"
          - "8000"
          - "--enable-lora"
          - "--lora-modules"
          - '{"name": "tweet-summary-0", "path": "/adapters/hub/models--ai-blond--Qwen-Qwen2.5-Coder-1.5B-Instruct-lora/snapshots/9cde18d8ed964b0519fb481cca6acd936b2ca811"}'
          - '{"name": "tweet-summary-1", "path": "/adapters/hub/models--ai-blond--Qwen-Qwen2.5-Coder-1.5B-Instruct-lora/snapshots/9cde18d8ed964b0519fb481cca6acd936b2ca811"}'
          env:
            - name: PORT
              value: "8000"
            - name: HUGGING_FACE_HUB_TOKEN
              valueFrom:
                secretKeyRef:
                  name: hf-token
                  key: token
            - name: VLLM_ALLOW_RUNTIME_LORA_UPDATING
              value: "true"
          ports:
            - containerPort: 8000
              name: http
              protocol: TCP
          livenessProbe:
            failureThreshold: 240
            httpGet:
              path: /health
              port: http
              scheme: HTTP
            initialDelaySeconds: 5
            periodSeconds: 5
            successThreshold: 1
            timeoutSeconds: 1
          readinessProbe:
            failureThreshold: 600
            httpGet:
              path: /health
              port: http
              scheme: HTTP
            initialDelaySeconds: 5
            periodSeconds: 5
            successThreshold: 1
            timeoutSeconds: 1
          volumeMounts:
            - mountPath: /data
              name: data
            - mountPath: /dev/shm
              name: shm
            - name: adapters
              mountPath: "/adapters"
      initContainers:
        - name: adapter-loader
          image: ghcr.io/tomatillo-and-multiverse/adapter-puller:demo
          command: ["python"]
          args:
            - ./pull_adapters.py
            - --adapter
            - ai-blond/Qwen-Qwen2.5-Coder-1.5B-Instruct-lora
            - --duplicate-count
            - "4"
          env:
            - name: HF_TOKEN 
              valueFrom:
                secretKeyRef:
                  name: hf-token
                  key: token
            - name: HF_HOME
              value: /adapters
          volumeMounts:
            - name: adapters
              mountPath: "/adapters"
      restartPolicy: Always
      schedulerName: default-scheduler
      terminationGracePeriodSeconds: 30
      volumes:
        - name: data
          emptyDir: {}
        - name: shm
          emptyDir:
            medium: Memory
        - name: adapters
          emptyDir: {}