apiVersion: ray.io/v1
kind: RayCluster
metadata:
  name: raycluster
  namespace: ray-system
spec:
  rayVersion: "2.41.0.dev0"
  headGroupSpec:
    serviceType: ClusterIP
    rayStartParams:
      num-cpus: "0"
      dashboard-host: "0.0.0.0"
      dashboard: "true"
    template:
      spec:
        tolerations:
        - key: "desktop"
          operator: "Equal"
          value: "true"
          effect: "NoSchedule"
        containers:
        - name: ray-head
          image: rayproject/ray:nightly-py313-gpu
          ports:
          - containerPort: 6379
            name: gcs
          - containerPort: 8265
            name: dashboard
          - containerPort: 10001
            name: client
          - containerPort: 8000
            name: serve
          resources:
            requests:
              cpu: "2"
              memory: "4Gi"
            limits:
              cpu: "4"
              memory: "8Gi"
          volumeMounts:
          - name: dshm
            mountPath: /dev/shm
          - name: dri
            mountPath: /dev/dri
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 2Gi
        - name: dri
          hostPath:
            path: /dev/dri
        nodeSelector:
          kubernetes.io/hostname: qfox-1
  workerGroupSpecs:
  - replicas: 2
    minReplicas: 0
    maxReplicas: 6
    groupName: cpu-workers
    rayStartParams:
      num-cpus: "4"
    template:
      spec:
        tolerations:
        - key: "desktop"
          operator: "Equal"
          value: "true"
          effect: "NoSchedule"
        containers:
        - name: ray-worker
          image: rayproject/ray:nightly-py313-gpu
          resources:
            requests:
              cpu: "4"
              memory: "4Gi"
            limits:
              cpu: "8"
              memory: "8Gi"
          volumeMounts:
          - name: dshm
            mountPath: /dev/shm
          - name: dri
            mountPath: /dev/dri
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 2Gi
        - name: dri
          hostPath:
            path: /dev/dri
        nodeSelector:
          kubernetes.io/hostname: qfox-1
  - replicas: 1
    minReplicas: 0
    maxReplicas: 1
    groupName: gpu-workers
    rayStartParams:
      num-gpus: "1"
    template:
      spec:
        tolerations:
        - key: "desktop"
          operator: "Equal"
          value: "true"
          effect: "NoSchedule"
        containers:
        - name: ray-worker
          image: rayproject/ray:nightly-py313-gpu
          resources:
            requests:
              cpu: "2"
              memory: "8Gi"
            limits:
              cpu: "4"
              memory: "16Gi"
          volumeMounts:
          - name: dshm
            mountPath: /dev/shm
          - name: dri
            mountPath: /dev/dri
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 4Gi
        - name: dri
          hostPath:
            path: /dev/dri
        nodeSelector:
          kubernetes.io/hostname: qfox-1
  - replicas: 1
    minReplicas: 0
    maxReplicas: 3
    groupName: arm64-workers
    rayStartParams:
      num-cpus: "16"
    template:
      spec:
        containers:
        - name: ray-worker
          image: localhost/rayproject/ray:arm64-aarch64
          resources:
            requests:
              cpu: "8"
              memory: "16Gi"
            limits:
              cpu: "16"
              memory: "56Gi"
          volumeMounts:
          - name: dshm
            mountPath: /dev/shm
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 8Gi
        nodeSelector:
          kubernetes.io/arch: arm64
          kubernetes.io/hostname: neon-64gb