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: "false"
    template:
      spec:
        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
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 2Gi
        nodeSelector:
          kubernetes.io/hostname: steamdeck
  workerGroupSpecs:
  - replicas: 1
    minReplicas: 0
    maxReplicas: 3
    groupName: cpu-workers
    rayStartParams:
      num-cpus: "2"
    template:
      spec:
        containers:
        - name: ray-worker
          image: rayproject/ray:nightly-py313-gpu
          resources:
            requests:
              cpu: "1"
              memory: "1Gi"
            limits:
              cpu: "2"
              memory: "2Gi"
          volumeMounts:
          - name: dshm
            mountPath: /dev/shm
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 1Gi
        nodeSelector:
          kubernetes.io/hostname: steamdeck
  - replicas: 0
    minReplicas: 0
    maxReplicas: 2
    groupName: gpu-workers
    rayStartParams:
      num-gpus: "1"
    template:
      spec:
        containers:
        - name: ray-worker
          image: rayproject/ray:nightly-py313-gpu
          resources:
            requests:
              cpu: "2"
              memory: "8Gi"
              nvidia.com/gpu: "1"
            limits:
              cpu: "4"
              memory: "16Gi"
              nvidia.com/gpu: "1"
          volumeMounts:
          - name: dshm
            mountPath: /dev/shm
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 4Gi
        nodeSelector:
          kubernetes.io/hostname: neon-64gb
        tolerations:
        - key: "nvidia.com/gpu"
          operator: "Exists"
          effect: "NoSchedule"
  - replicas: 0
    minReplicas: 0
    maxReplicas: 1
    groupName: arm64-workers
    rayStartParams:
      num-cpus: "4"
    template:
      spec:
        containers:
        - name: ray-worker
          image: rayproject/ray:nightly-py313-gpu
          resources:
            requests:
              cpu: "4"
              memory: "8Gi"
            limits:
              cpu: "8"
              memory: "16Gi"
          volumeMounts:
          - name: dshm
            mountPath: /dev/shm
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 4Gi
        nodeSelector:
          kubernetes.io/hostname: neon-64gb
          kubernetes.io/arch: arm64