cluster.yaml

cluster_name: repro-issue-13090

min_workers: 0
max_workers: 0

docker:
    image: anyscale/ray-ml:latest
    container_name: ray_container
    pull_before_run: True

# Cloud-provider specific configuration.
provider:
    type: aws
    region: us-west-2
    availability_zone: us-west-2a
    cache_stopped_nodes: False

# How Ray will authenticate with newly launched nodes.
auth:
    ssh_user: ubuntu

head_node:
    InstanceType: m4.xlarge
    ImageId: ami-0a2363a9cff180a64 # Custom ami
    # Set primary volume to 25 GiB
    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 100

worker_nodes:
    InstanceType: m4.xlarge
    ImageId: ami-0a2363a9cff180a64 # Custom ami
    # Set primary volume to 25 GiB
    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 100

# List of shell commands to run to set up nodes.
setup_commands:
    - pip install torch==1.6 torchvision

# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
    - ray stop
    - ray start --head --port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml

# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
    - ray stop
    - ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076