# An unique identifier for the head node and workers of this cluster.
cluster_name: gpu-docker

# The maximum number of workers nodes to launch in addition to the head
# node.
max_workers: 2

# The autoscaler will scale up the cluster faster with higher upscaling speed.
# E.g., if the task requires adding more nodes then autoscaler will gradually
# scale up the cluster in chunks of upscaling_speed*currently_running_nodes.
# This number should be > 0.
upscaling_speed: 1.0

# This executes all commands on all nodes in the docker container,
# and opens all the necessary ports to support the Ray cluster.
# Empty string means disabled.
docker:
    image: "rayproject/ray-ml:latest-gpu"
    # image: rayproject/ray:latest-gpu   # use this one if you don't need ML dependencies, it's faster to pull
    container_name: "ray_nvidia_docker"

    # # Example of running a GPU head with CPU workers
    # head_image: "rayproject/ray-ml:latest-gpu"

    # worker_image: "rayproject/ray-ml:latest"

# If a node is idle for this many minutes, it will be removed.
idle_timeout_minutes: 5

# Cloud-provider specific configuration.
provider:
    type: azure
    location: westus2
    resource_group: ray-cluster
    # set subscription id otherwise the default from az cli will be used
    # subscription_id: 00000000-0000-0000-0000-000000000000
    # set unique subnet mask or a random mask will be used
    # subnet_mask: 10.0.0.0/16
    # set unique id for resources in this cluster
    # if not set a default id will be generated based on the resource group and cluster name
    # unique_id: RAY1

# How Ray will authenticate with newly launched nodes.
auth:
    ssh_user: ubuntu
    # SSH keys will be auto-generated with Ray-specific names if not specified
    # Uncomment and specify custom paths if you want to use different existing keys:
    # ssh_private_key: /path/to/your/key.pem
    # ssh_public_key: /path/to/your/key.pub

# Tell the autoscaler the allowed node types and the resources they provide.
# The key is the name of the node type, which is just for debugging purposes.
# The node config specifies the launch config and physical instance type.
available_node_types:
    ray.head.gpu:
        # The resources provided by this node type.
        resources: {"CPU": 6, "GPU": 1}
        # Provider-specific config, e.g. instance type.
        node_config:
            azure_arm_parameters:
                vmSize: Standard_NC6s_v3
                # List images https://docs.microsoft.com/en-us/azure/virtual-machines/linux/cli-ps-findimage
                imagePublisher: microsoft-dsvm
                imageOffer: ubuntu-2204
                imageSku: 2204-gen2
                imageVersion: latest

    ray.worker.gpu:
        # The minimum number of nodes of this type to launch.
        # This number should be >= 0.
        min_workers: 0
        # The maximum number of workers nodes of this type to launch.
        # This takes precedence over min_workers.
        max_workers: 2
        # The resources provided by this node type.
        resources: {"CPU": 6, "GPU": 1}
        # Provider-specific config, e.g. instance type.
        node_config:
            azure_arm_parameters:
                vmSize: Standard_NC6s_v3
                # List images https://docs.microsoft.com/en-us/azure/virtual-machines/linux/cli-ps-findimage
                imagePublisher: microsoft-dsvm
                imageOffer: ubuntu-2204
                imageSku: 2204-gen2
                imageVersion: latest
                # optionally set priority to use Spot instances
                priority: Spot
                # set a maximum price for spot instances if desired
                # billingProfile:
                #     maxPrice: -1

# Specify the node type of the head node (as configured above).
head_node_type: ray.head.gpu

# Files or directories to copy to the head and worker nodes. The format is a
# dictionary from REMOTE_PATH: LOCAL_PATH, e.g.
file_mounts: {
#    "/path1/on/remote/machine": "/path1/on/local/machine",
#    "/path2/on/remote/machine": "/path2/on/local/machine",
}

# List of commands that will be run before `setup_commands`. If docker is
# enabled, these commands will run outside the container and before docker
# is setup.
initialization_commands:
    # enable docker setup
    - sudo usermod -aG docker $USER || true
    - sleep 10  # delay to avoid docker permission denied errors
    # get rid of annoying Ubuntu message
    - touch ~/.sudo_as_admin_successful

# List of shell commands to run to set up nodes.
# NOTE: rayproject/ray-ml:latest has ray latest bundled
setup_commands: []
#     - pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp38-cp38-manylinux2014_x86_64.whl"

# Custom commands that will be run on the head node after common setup.
head_setup_commands:
    - pip install -U azure-core==1.35.0 azure-cli-core==2.77.0 azure-identity==1.23.1 azure-mgmt-compute==35.0.0 azure-mgmt-network==29.0.0 azure-mgmt-resource==24.0.0 azure-common==1.1.28 msrest==0.7.1 msrestazure==0.6.4.post1

# Custom commands that will be run on worker nodes after common setup.
worker_setup_commands: []

# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
    - ray stop
    - ulimit -n 65536; 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
    - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076