chore: import upstream snapshot with attribution

python/ray/autoscaler/azure/BUILD.bazel

@@ -0,0 +1,17 @@
+filegroup(
+    name = "example",
+    data = glob(["example-*.yaml"]),
+    visibility = ["//python/ray/tests:__pkg__"],
+)
+
+filegroup(
+    name = "default_config",
+    srcs = ["defaults.yaml"],
+    visibility = ["//visibility:public"],
+)
+
+filegroup(
+    name = "test_configs",
+    data = glob(["tests/*.yaml"]),
+    visibility = ["//release:__pkg__"],
+)

python/ray/autoscaler/azure/defaults.yaml

@@ -0,0 +1,164 @@
+# An unique identifier for the head node and workers of this cluster.
+cluster_name: default
+
+# 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 object means disabled.
+docker: {}
+
+# If a node is idle for this many minutes, it will be removed.
+idle_timeout_minutes: 5
+
+# Cloud-provider specific configuration.
+provider:
+    type: azure
+    # https://azure.microsoft.com/en-us/global-infrastructure/locations
+    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
+    # Availability zones for VM placement (comma-separated). Examples:
+    # availability_zone: "1,2,3"  # Use zones 1, 2, and 3
+    # availability_zone: "1"      # Use only zone 1
+    # availability_zone: "none"   # Explicitly disable zones
+    availability_zone: "auto"    # Let Azure automatically pick zones
+
+
+# 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
+
+# More specific customization to node configurations can be made using the ARM template azure-vm-template.json file
+# See documentation here: https://docs.microsoft.com/en-us/azure/templates/microsoft.compute/2019-03-01/virtualmachines
+# Changes to the local file will be used during deployment of the head node, however worker nodes deployment occurs
+# on the head node, so changes to the template must be included in the wheel file used in setup_commands section below
+
+# 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.default:
+        resources: {"CPU": 2}
+        # Provider-specific config, e.g. instance type.
+        node_config:
+            azure_arm_parameters:
+                vmSize: Standard_D2s_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
+                # Head node: explicitly disable availability zones
+                availability_zone: "none"
+
+    ray.worker.default:
+        # The minimum number of nodes of this type to launch.
+        # This number should be >= 0.
+        min_workers: 0
+        # The resources provided by this node type.
+        resources: {"CPU": 2}
+        # Provider-specific config, e.g. instance type.
+        node_config:
+            azure_arm_parameters:
+                vmSize: Standard_D2s_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
+                # comment lines below to not use Spot instances
+                priority: Spot
+                # set a maximum price for spot instances if desired
+                # billingProfile:
+                #     maxPrice: -1
+                # Workers: inherit provider availability_zone setting
+                # Options: "1,2,3" for specific zones, "none" to disable zones,
+                #  or "auto" to let Azure pick zones automatically
+
+# Specify the node type of the head node (as configured above).
+head_node_type: ray.head.default
+
+# 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",
+}
+
+# Files or directories to copy from the head node to the worker nodes. The format is a
+# list of paths. The same path on the head node will be copied to the worker node.
+# This behavior is a subset of the file_mounts behavior. In the vast majority of cases
+# you should just use file_mounts. Only use this if you know what you're doing!
+cluster_synced_files: []
+
+# Whether changes to directories in file_mounts or cluster_synced_files in the head node
+# should sync to the worker node continuously
+file_mounts_sync_continuously: False
+
+# Patterns for files to exclude when running rsync up or rsync down
+rsync_exclude: []
+
+# Pattern files to use for filtering out files when running rsync up or rsync down. The file is searched for
+# in the source directory and recursively through all subdirectories. For example, if .gitignore is provided
+# as a value, the behavior will match git's behavior for finding and using .gitignore files.
+rsync_filter: []
+
+# 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:
+    # get rid of annoying Ubuntu message
+    - touch ~/.sudo_as_admin_successful
+
+# List of shell commands to run to set up nodes.
+setup_commands:
+    # Note: if you're developing Ray, you probably want to create an AMI that
+    # has your Ray repo pre-cloned. Then, you can replace the pip installs
+    # below with a git checkout <your_sha> (and possibly a recompile).
+    # Note: The Ubuntu 22.04 dsvm image has a few venvs already configured but
+    # they all contain python modules that are not compatible with Ray at the moment.
+    - (which conda && echo 'eval "$(conda shell.bash hook)"' >> ~/.bashrc) || true
+    - conda tos accept
+    - conda create -n ray-env python=3.10 -y
+    - conda activate ray-env && echo 'conda activate ray-env' >> ~/.bashrc
+    - which ray || pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp310-cp310-manylinux2014_x86_64.whl"
+    # Consider uncommenting these if you also want to run apt-get commands during setup
+    # - sudo pkill -9 apt-get || true
+    # - sudo pkill -9 dpkg || true
+    # - sudo dpkg --configure -a
+
+# Custom commands that will be run on the head node after common setup.
+head_setup_commands:
+    - pip install -U azure-core==1.35.0 azure-identity==1.23.1 azure-mgmt-compute==35.0.0 azure-mgmt-network==29.0.0 azure-mgmt-resource==24.0.0 azure-common==1.1.28 msrest==0.7.1 msrestazure==0.6.4.post1
+
+# Custom commands that will be run on worker nodes after common setup.
+worker_setup_commands: []
+
+# Command to start ray on the head node. You don't need to change this.
+head_start_ray_commands:
+    - ray stop
+    - ulimit -n 65536; ray start --head --port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml --dashboard-host=0.0.0.0
+
+# Command to start ray on worker nodes. You don't need to change this.
+worker_start_ray_commands:
+    - ray stop
+    - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076

python/ray/autoscaler/azure/example-availability-zones.yaml

@@ -0,0 +1,70 @@
+# Unique identifier for the head node and workers of this cluster.
+cluster_name: nightly-cpu-minimal-2
+max_workers: 6
+idle_timeout_minutes: 5
+
+# Cloud-provider specific configuration.
+provider:
+  type: azure
+    # https://azure.microsoft.com/en-us/global-infrastructure/locations
+  location: westus2
+  resource_group: ray-zones
+  cache_stopped_nodes: False
+  # Provider-level availability zone configuration (comma-separated)
+  # This will be used as default for all node types unless overridden
+  availability_zone: "1,2,3"
+
+auth:
+  ssh_user: ubuntu
+
+available_node_types:
+  ray.head.default:
+    resources: {"CPU": 2}
+    node_config:
+      azure_arm_parameters:
+        vmSize: Standard_D2s_v3
+        imagePublisher: microsoft-dsvm
+        imageOffer: ubuntu-2204
+        imageSku: 2204-gen2
+        imageVersion: latest
+        # Head node: explicitly disable availability zones
+        availability_zone: "none"
+  ray.worker.default:
+    min_workers: 0
+    max_workers: 2
+    resources: {"CPU": 2}
+    node_config:
+      azure_arm_parameters:
+        vmSize: Standard_D2s_v3
+        imagePublisher: microsoft-dsvm
+        imageOffer: ubuntu-2204
+        imageSku: 2204-gen2
+        imageVersion: latest
+        # Workers will use provider specified availability zones
+  ray.worker.specific_zone:
+    min_workers: 0
+    max_workers: 2
+    resources: {"CPU": 2}
+    node_config:
+      azure_arm_parameters:
+        vmSize: Standard_D2s_v3
+        imagePublisher: microsoft-dsvm
+        imageOffer: ubuntu-2204
+        imageSku: 2204-gen2
+        imageVersion: latest
+        # Workers will use availability zone 2 only (overrides provider setting)
+        availability_zone: "2"
+
+# Note: The Ubuntu 20.04 dsvm image has a few venvs already configured but
+# they all contain python modules that are not compatible with Ray at the moment.
+setup_commands:
+    - (which conda && echo 'eval "$(conda shell.bash hook)"' >> ~/.bashrc) || true
+    - conda tos accept
+    - conda create -n ray-env python=3.10 -y
+    - conda activate ray-env && echo 'conda activate ray-env' >> ~/.bashrc
+    - which ray || pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp310-cp310-manylinux2014_x86_64.whl"
+
+file_mounts_sync_continuously: False
+
+file_mounts: {
+}

python/ray/autoscaler/azure/example-full.yaml

@@ -0,0 +1,187 @@
+# A unique identifier for the head node and workers of this cluster.
+cluster_name: default
+
+# 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 object means disabled.
+docker:
+    image: "rayproject/ray-ml:latest-gpu" # You can change this to latest-cpu if you don't need GPU support and want a faster startup
+    # image: rayproject/ray:latest-gpu   # use this one if you don't need ML dependencies, it's faster to pull
+    container_name: "ray_container"
+    # If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
+    # if no cached version is present.
+    pull_before_run: True
+    run_options: # Extra options to pass into "docker run"
+        - --ulimit nofile=65536:65536
+
+    # Example of running a GPU head with CPU workers
+    # head_image: "rayproject/ray-ml:latest-gpu"
+    # Allow Ray to automatically detect GPUs
+
+    # worker_image: "rayproject/ray-ml:latest-cpu"
+    # worker_run_options: []
+
+# If a node is idle for this many minutes, it will be removed.
+idle_timeout_minutes: 5
+
+# Cloud-provider specific configuration.
+provider:
+    type: azure
+    # https://azure.microsoft.com/en-us/global-infrastructure/locations
+    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
+    # Set managed identity name and resource group;
+    # If not set, a default user-assigned identity will be generated in the resource group specified above.
+    # msi_name: ray-cluster-msi
+    # msi_resource_group: other-rg
+    # Set provisioning and use of public/private IPs for head and worker nodes;
+    # If both options below are true, only the head node will have a public IP address provisioned.
+    # use_internal_ips: True
+    # use_external_head_ip: True
+
+# 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
+
+# You can make more specific customization to node configurations can be made using the ARM template azure-vm-template.json file.
+# See this documentation here: https://docs.microsoft.com/en-us/azure/templates/microsoft.compute/2019-03-01/virtualmachines
+# Changes to the local file will be used during deployment of the head node, however worker nodes deployment occurs
+# on the head node, so changes to the template must be included in the wheel file used in setup_commands section below
+
+# 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.default:
+        # The resources provided by this node type.
+        resources: {"CPU": 4}
+        # Provider-specific config, e.g. instance type.
+        node_config:
+            azure_arm_parameters:
+                vmSize: Standard_D4s_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
+
+                # Or, use a custom image from Azure Compute Gallery.
+                # Note: if you use a custom image, then imagePublisher,
+                # imageOffer, imageSku, and imageVersion are ignored.
+                # imageId: /subscriptions/[subscription-id]/resourceGroups/[resource-group-id]/providers/Microsoft.Compute/galleries/[azure-compute-gallery-id]/images/[image-id]/versions/[image-version]
+
+                # Optionally set osDiskSize if you want to use a custom disk size.
+                # osDiskSize: 128
+
+    ray.worker.default:
+        # The minimum number of worker nodes of this type to launch.
+        # This number should be >= 0.
+        min_workers: 0
+        # The maximum number of worker nodes of this type to launch.
+        # This takes precedence over min_workers.
+        max_workers: 2
+        # The resources provided by this node type.
+        resources: {"CPU": 4}
+        # Provider-specific config, e.g. instance type.
+        node_config:
+            azure_arm_parameters:
+                vmSize: Standard_D4s_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.default
+
+# 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",
+}
+
+# Files or directories to copy from the head node to the worker nodes. The format is a
+# list of paths. Ray copies the same path on the head node to the worker node.
+# This behavior is a subset of the file_mounts behavior. In the vast majority of cases
+# you should just use file_mounts. Only use this if you know what you're doing!
+cluster_synced_files: []
+
+# Whether changes to directories in file_mounts or cluster_synced_files in the head node
+# should sync to the worker node continuously.
+file_mounts_sync_continuously: False
+
+# Patterns for files to exclude when running rsync up or rsync down.
+rsync_exclude:
+    - "**/.git"
+    - "**/.git/**"
+
+# Pattern files to use for filtering out files when running rsync up or rsync down. The file is searched for
+# in the source directory and recursively through all subdirectories. For example, if .gitignore is provided
+# as a value, the behavior will match git's behavior for finding and using .gitignore files.
+rsync_filter:
+    - ".gitignore"
+
+# 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 $USER || true
+    - sleep 10 # delay to avoid docker permission denied errors
+    # get rid of annoying Ubuntu message
+    - touch ~/.sudo_as_admin_successful
+
+# List of shell commands to run to set up nodes.
+# NOTE: rayproject/ray-ml:latest has ray latest bundled
+setup_commands: []
+# Note: if you're developing Ray, you probably want to create a Docker image that
+# has your Ray repo pre-cloned. Then, you can replace the pip installs
+# below with a git checkout <your_sha> (and possibly a recompile).
+# To run the nightly version of ray (as opposed to the latest), either use a rayproject docker image
+# that has the "nightly" (e.g. "rayproject/ray-ml:nightly-gpu") or uncomment the following line:
+# - pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp38-cp38-manylinux2014_x86_64.whl"
+
+# Custom commands that will be run on the head node after common setup.
+head_setup_commands:
+    - pip install -U azure-core==1.35.0 azure-cli-core==2.77.0 azure-identity==1.23.1 azure-mgmt-compute==35.0.0 azure-mgmt-network==29.0.0 azure-mgmt-resource==24.0.0 azure-common==1.1.28 msrest==0.7.1 msrestazure==0.6.4.post1
+
+# Custom commands that will be run on worker nodes after common setup.
+worker_setup_commands: []
+
+# Command to start ray on the head node. You don't need to change this.
+head_start_ray_commands:
+    - ray stop
+    - ray start --head --port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml
+
+# Command to start ray on worker nodes. You don't need to change this.
+worker_start_ray_commands:
+    - ray stop
+    - ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076

python/ray/autoscaler/azure/example-gpu-docker.yaml

@@ -0,0 +1,132 @@
+# 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

python/ray/autoscaler/azure/example-minimal.yaml

@@ -0,0 +1,27 @@
+# An unique identifier for the head node and workers of this cluster.
+cluster_name: minimal
+
+# The maximum number of workers nodes to launch in addition to the head
+# node. min_workers default to 0.
+max_workers: 2
+
+# Cloud-provider specific configuration.
+provider:
+    type: azure
+    location: westus2
+    resource_group: ray-cluster
+
+# 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
+
+# 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",
+}

python/ray/autoscaler/azure/tests/azure-cluster.yaml

@@ -0,0 +1,57 @@
+# Unique identifier for the head node and workers of this cluster.
+cluster_name: nightly-cpu-minimal-centralus
+max_workers: 2
+idle_timeout_minutes: 5
+
+# Cloud-provider specific configuration.
+provider:
+  type: azure
+  # https://azure.microsoft.com/en-us/global-infrastructure/locations
+  location: centralus
+  resource_group: ray-nightly-cpu-minimal-centralus
+  cache_stopped_nodes: False
+
+auth:
+  ssh_user: ubuntu
+  ssh_private_key: "~/.ssh/ray-autoscaler-tests-ssh-key"
+  ssh_public_key: "~/.ssh/ray-autoscaler-tests-ssh-key.pub"
+
+available_node_types:
+  ray.head.default:
+    resources: {"CPU": 2}
+    node_config:
+      azure_arm_parameters:
+        vmSize: Standard_D2s_v3
+        imagePublisher: microsoft-dsvm
+        imageOffer: ubuntu-2204
+        imageSku: 2204-gen2
+        imageVersion: latest
+  ray.worker.default:
+    min_workers: 2
+    max_workers: 2
+    resources: {"CPU": 2}
+    node_config:
+      azure_arm_parameters:
+        vmSize: Standard_D2s_v3
+        imagePublisher: microsoft-dsvm
+        imageOffer: ubuntu-2204
+        imageSku: 2204-gen2
+        imageVersion: latest
+
+# Note: The Ubuntu 22.04 dsvm image has a few venvs already configured but
+# they all contain python modules that are not compatible with Ray at the moment.
+setup_commands:
+    - (which conda && echo 'eval "$(conda shell.bash hook)"' >> ~/.bashrc) || true
+    - conda tos accept
+    - conda create -n ray-env python=3.10 -y
+    - conda activate ray-env && echo 'conda activate ray-env' >> ~/.bashrc
+    - which ray || pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp310-cp310-manylinux2014_x86_64.whl"
+
+file_mounts_sync_continuously: False
+
+file_mounts: {
+     "~/.ssh/ray-autoscaler-tests-ssh-key.pub": "~/.ssh/ray-autoscaler-tests-ssh-key.pub"
+}
+
+head_setup_commands:
+- pip install azure-core==1.35.0 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

python/ray/autoscaler/azure/tests/azure_compute.yaml

@@ -0,0 +1,15 @@
+# This test launches an Azure VM cluster from an AWS instance.
+# The test script runs on AWS while the actual cluster is created in Azure.
+cloud_id: {{env["ANYSCALE_CLOUD_ID"]}}
+region: us-west-2
+
+head_node_type:
+    name: head_node
+    instance_type: t3.large
+
+worker_node_types:
+    - name: worker_node
+      instance_type: t3.large
+      min_workers: 0
+      max_workers: 0
+      use_spot: false