apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: llama-31-8b-sglang
spec:
  accessModes:
    - ReadWriteMany
  resources:
    requests:
      storage: 30Gi
  storageClassName: default # change this to your preferred storage class
  volumeMode: Filesystem
---
apiVersion: node.k8s.io/v1
kind: RuntimeClass
metadata:
  name: nvidia
handler: nvidia
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: meta-llama-31-8b-instruct-sglang
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: meta-llama-31-8b-instruct-sglang
  template:
    metadata:
      labels:
        app: meta-llama-31-8b-instruct-sglang
        model: meta-llama-31-8b-instruct
        engine: sglang
    spec:
      restartPolicy: Always
      runtimeClassName: nvidia
      containers:
        - name: meta-llama-31-8b-instruct-sglang
          image: docker.io/lmsysorg/sglang:latest
          imagePullPolicy: Always # IfNotPresent or Never
          ports:
            - containerPort: 30000
          command: ["python3", "-m", "sglang.launch_server"]
          args:
            [
              "--model-path",
              "meta-llama/Llama-3.1-8B-Instruct",
              "--host",
              "0.0.0.0",
              "--port",
              "30000",
            ]
          env:
            - name: HF_TOKEN
              value: <secret>
          resources:
            limits:
              nvidia.com/gpu: 1
              cpu: 8
              memory: 40Gi
            requests:
              cpu: 2
              memory: 16Gi
              nvidia.com/gpu: 1
          volumeMounts:
            - name: shm
              mountPath: /dev/shm
            - name: hf-cache
              mountPath: /root/.cache/huggingface
            - name: localtime
              mountPath: /etc/localtime
              readOnly: true
          livenessProbe:
            httpGet:
              path: /health
              port: 30000
            initialDelaySeconds: 120
            periodSeconds: 15
            timeoutSeconds: 10
            failureThreshold: 3
          readinessProbe:
            httpGet:
              path: /health_generate
              port: 30000
            initialDelaySeconds: 120
            periodSeconds: 15
            timeoutSeconds: 10
            failureThreshold: 3
            successThreshold: 1
      volumes:
        - name: shm
          emptyDir:
            medium: Memory
            sizeLimit: 10Gi
        - name: hf-cache
          persistentVolumeClaim:
            claimName: llama-31-8b-sglang
        - name: localtime
          hostPath:
            path: /etc/localtime
            type: File
---
apiVersion: v1
kind: Service
metadata:
  name: meta-llama-31-8b-instruct-sglang
spec:
  selector:
    app: meta-llama-31-8b-instruct-sglang
  ports:
    - protocol: TCP
      port: 80 # port on host
      targetPort: 30000 # port in container
  type: LoadBalancer # change to ClusterIP if needed