deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-llama2-7b-pool
spec:
  replicas: 6
  selector:
    matchLabels:
      app: vllm-llama2-7b-pool
  template:
    metadata:
      labels:
        app: vllm-llama2-7b-pool
    spec:
      containers:
        - name: lora
          image: "vllm/vllm-openai:latest"
          imagePullPolicy: Always
          command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
          args:
          - "--model"
          - "meta-llama/Llama-2-7b-hf"
          - "--tensor-parallel-size"
          - "1"
          - "--port"
          - "8000"
          - "--compilation-config"
          - "3"
          - "--max-num-seqs"
          - "2048"
          - "--enable-lora"
          - "--max-loras"
          - "4"
          - "--max-cpu-loras"
          - "15"
          - "--max-lora-rank"
          - "16"
          - "--lora-modules"
          - '{"name": "tweet-summary-0", "path": "vineetsharma/qlora-adapter-Llama-2-7b-hf-TweetSumm", "base_model_name": "llama-2"}'
          - '{"name": "tweet-summary-1", "path": "vineetsharma/qlora-adapter-Llama-2-7b-hf-TweetSumm", "base_model_name": "llama-2"}'
          env:
            - name: VLLM_USE_V1
              value: "1"
            - 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
          resources:
            limits:
              nvidia.com/gpu: 1
            requests:
              nvidia.com/gpu: 1
          volumeMounts:
            - mountPath: /data
              name: data
            - mountPath: /dev/shm
              name: shm
            - name: adapters
              mountPath: "/adapters"
      initContainers:
        - name: lora-adapter-syncer
          tty: true
          stdin: true 
          image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/lora-syncer:main
          restartPolicy: Always
          imagePullPolicy: Always
          env: 
            - name: DYNAMIC_LORA_ROLLOUT_CONFIG
              value: "/config/configmap.yaml"
          volumeMounts: # DO NOT USE subPath, dynamic configmap updates don't work on subPaths
          - name: config-volume
            mountPath:  /config
      restartPolicy: Always
      schedulerName: default-scheduler
      terminationGracePeriodSeconds: 30
      volumes:
        - name: data
          emptyDir: {}
        - name: shm
          emptyDir:
            medium: Memory
        - name: adapters
          emptyDir: {}
        - name: config-volume
          configMap:
            name: vllm-llama2-7b-adapters
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: vllm-llama2-7b-adapters
data:
  configmap.yaml: |
      vLLMLoRAConfig:
        name: vllm-llama2-7b
        port: 8000
        ensureExist:
          models:
          - base-model: meta-llama/Llama-2-7b-hf
            id: tweet-summary-1
            source: vineetsharma/qlora-adapter-Llama-2-7b-hf-TweetSumm