manifest.yml

# yaml-language-server: $schema=https://instadeep.aichor.ai/schema/latest/manifest.schema.json

kind: AIchorManifest
apiVersion: 0.2.2

builder:
  image: railsim
  dockerfile: ./Dockerfile
  context: .

spec:
  operator: ray
  image: melqart
  command: "python train.py"
  rayVersion: "v2.2"

  tensorboard: # optional, disabled by default
    enabled: true

  storage: # optional
    sharedVolume: # optional
      mountPoint: "/mnt/shared"
      sizeGB: 16
    attachExistingPVCs: # optional, array
      - name: "my-awesome-pvc"
        mountPoint: "/mnt/my-60tib-dataset"

  # Ray types are: Head, Job, Workers
  # They are all required
  # At least one worker must be set
  types:
    Head:
      ports: [] # optional
      resources:
        cpus: 10
        ramRatio: 2

        # machineName: "dgx" # optional
        shmSizeGB: 48 # optional

        accelerators: # optional
          gpu:
            count: 2
            product: Tesla-V100-SXM3-32GB
            type: gpu

    Job:
      ports: [] # optional
      resources:
        cpus: 10
        ramRatio: 2

        # machineName: "node007" # optional
        shmSizeGB: 0 # optional

    Workers:
      - name: "cpu-workers"
        count: 2
        ports: [] # optional
        resources:
          cpus: 1
          ramRatio: 2
          # machineName: "node007" # optional
          shmSizeGB: 0 # optional