chore: import upstream snapshot with attribution

python/ray/autoscaler/gcp/BUILD.bazel

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

python/ray/autoscaler/gcp/defaults.yaml

@@ -0,0 +1,171 @@
+# 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 string 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: gcp
+    region: us-west1
+    availability_zone: us-west1-a
+    project_id: null # Globally unique project id
+
+# How Ray will authenticate with newly launched nodes.
+auth:
+    ssh_user: ubuntu
+# By default Ray creates a new private keypair, but you can also use your own.
+# If you do so, make sure to also set "KeyName" in the head and worker node
+# configurations below. This requires that you have added the key into the
+# project wide meta-data.
+#    ssh_private_key: /path/to/your/key.pem
+
+# 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": 2}
+        # Provider-specific config for this node type, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/deeplearning-platform-release/global/images/family/common-cpu
+
+            # Additional options can be found in in the compute docs at
+            # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+
+            # If the network interface is specified as below in both head and worker
+            # nodes, the manual network config is used.  Otherwise an existing subnet is
+            # used.  To use a shared subnet, ask the subnet owner to grant permission
+            # for 'compute.subnetworks.use' to the ray autoscaler account...
+            # networkInterfaces:
+            #   - kind: compute#networkInterface
+            #     subnetwork: path/to/subnet
+            #     aliasIpRanges: []
+    ray_worker_small:
+        # 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 for this node type, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/deeplearning-platform-release/global/images/family/common-cpu
+            # Run workers on preemtible instance by default.
+            # Comment this out to use on-demand.
+            scheduling:
+              - preemptible: true
+
+    # Additional options can be found in in the compute docs at
+    # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+
+# 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: []
+
+# 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).
+    # - echo 'export PATH="$HOME/anaconda3/envs/tensorflow_p36/bin:$PATH"' >> ~/.bashrc
+    # Install ray if not present
+    - >-
+        (stat /opt/conda/bin/ &> /dev/null &&
+        echo 'export PATH="/opt/conda/bin:$PATH"' >> ~/.bashrc) || true
+    - which ray || pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl"
+
+
+# Custom commands that will be run on the head node after common setup.
+head_setup_commands:
+  - pip install google-api-python-client==1.7.8
+
+# Custom commands that will be run on worker nodes after common setup.
+worker_setup_commands: []
+
+# Command to start ray on the head node. You don't need to change this.
+head_start_ray_commands:
+    - ray stop
+    - >-
+      ulimit -n 65536;
+      ray start
+      --head
+      --port=6379
+      --object-manager-port=8076
+      --autoscaling-config=~/ray_bootstrap_config.yaml
+      --dashboard-host=0.0.0.0
+
+# Command to start ray on worker nodes. You don't need to change this.
+worker_start_ray_commands:
+    - ray stop
+    - >-
+      ulimit -n 65536;
+      ray start
+      --address=$RAY_HEAD_IP:6379
+      --object-manager-port=8076

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

@@ -0,0 +1,191 @@
+# 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 string 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: gcp
+    region: us-west1
+    availability_zone: us-west1-a
+    project_id: null # Globally unique project id
+
+# How Ray will authenticate with newly launched nodes.
+auth:
+    ssh_user: ubuntu
+# By default Ray creates a new private keypair, but you can also use your own.
+# If you do so, make sure to also set "KeyName" in the head and worker node
+# configurations below. This requires that you have added the key into the
+# project wide meta-data.
+#    ssh_private_key: /path/to/your/key.pem
+
+# 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": 2}
+        # Provider-specific config for the head node, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/deeplearning-platform-release/global/images/common-cpu-v20240922
+
+            # Additional options can be found in in the compute docs at
+            # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+
+            # If the network interface is specified as below in both head and worker
+            # nodes, the manual network config is used.  Otherwise an existing subnet is
+            # used.  To use a shared subnet, ask the subnet owner to grant permission
+            # for 'compute.subnetworks.use' to the ray autoscaler account...
+            # networkInterfaces:
+            #   - kind: compute#networkInterface
+            #     subnetwork: path/to/subnet
+            #     aliasIpRanges: []
+    ray_worker_small:
+        # The minimum number of worker nodes of this type to launch.
+        # This number should be >= 0.
+        min_workers: 1
+        # 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": 2}
+        # Provider-specific config for the head node, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/deeplearning-platform-release/global/images/common-cpu-v20240922
+            # Run workers on preemtible instance by default.
+            # Comment this out to use on-demand.
+            scheduling:
+              - preemptible: true
+            # Un-Comment this to launch workers with the Service Account of the Head Node
+            # serviceAccounts:
+            # - email: ray-autoscaler-sa-v1@<project_id>.iam.gserviceaccount.com
+            #   scopes:
+            #   - https://www.googleapis.com/auth/cloud-platform
+
+    # Additional options can be found in in the compute docs at
+    # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+
+# 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:
+    - "**/.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: []
+
+# List of shell commands to run to set up nodes.
+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-cp37-cp37m-manylinux2014_x86_64.whl"
+
+
+# Custom commands that will be run on the head node after common setup.
+head_setup_commands:
+  - pip install google-api-python-client==1.7.8
+
+# 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/gcp/example-gpu-docker.yaml

@@ -0,0 +1,166 @@
+# 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:latest-gpu"
+    # image: rayproject/ray-ml:latest-gpu   # use this one if you need ML dependencies, but it's slower to pull
+    container_name: "ray_nvidia_docker" # e.g. ray_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: gcp
+    region: us-west1
+    availability_zone: us-west1-b
+    project_id: null # Replace this with your globally unique project id
+
+# How Ray will authenticate with newly launched nodes.
+auth:
+    ssh_user: ubuntu
+# By default Ray creates a new private keypair, but you can also use your own.
+# If you do so, make sure to also set "KeyName" in the head and worker node
+# configurations below. This requires that you have added the key into the
+# project wide meta-data.
+#    ssh_private_key: /path/to/your/key.pem
+
+# 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 for the head node, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/ml-images/global/images/c0-deeplearning-common-cu121-v20231209-debian-11
+            # Make sure to set scheduling->onHostMaintenance to TERMINATE when GPUs are present
+            guestAccelerators:
+              - acceleratorType: nvidia-tesla-t4
+                acceleratorCount: 1
+            metadata:
+              items:
+                - key: install-nvidia-driver
+                  value: "True"
+            scheduling:
+              - onHostMaintenance: TERMINATE
+
+    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": 2, "GPU": 1}
+        # Provider-specific config for the head node, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/ml-images/global/images/c0-deeplearning-common-cu121-v20231209-debian-11
+            # Make sure to set scheduling->onHostMaintenance to TERMINATE when GPUs are present
+            guestAccelerators:
+              - acceleratorType: nvidia-tesla-t4
+                acceleratorCount: 1
+            metadata:
+              items:
+                - key: install-nvidia-driver
+                  value: "True"
+            # Run workers on preemtible instance by default.
+            # Comment this out to use on-demand.
+            scheduling:
+              - preemptible: true
+              - onHostMaintenance: TERMINATE
+
+# 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",
+}
+
+initialization_commands:
+    # Wait until nvidia drivers are installed
+    - >-
+      timeout 300 bash -c "
+          command -v nvidia-smi && nvidia-smi
+          until [ \$? -eq 0 ]; do
+              command -v nvidia-smi && nvidia-smi
+          done"
+
+# List of shell commands to run to set up nodes.
+# NOTE: rayproject/ray-ml:latest has ray latest bundled
+setup_commands: []
+    # - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl
+    # - pip install -U "ray[default] @ https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl"
+
+# Custom commands that will be run on the head node after common setup.
+head_setup_commands:
+  - pip install google-api-python-client==1.7.8
+
+# 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/gcp/example-minimal-pinned.yaml

@@ -0,0 +1,36 @@
+auth:
+  ssh_user: ubuntu
+cluster_name: minimal
+provider:
+  availability_zone: us-west1-a
+  project_id: null # TODO: set your GCP project ID here
+  region: us-west1
+  type: gcp
+
+# Needs to pin the VM images for stability..
+available_node_types:
+    ray_head_default:
+        resources: {"CPU": 2}
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  sourceImage: projects/deeplearning-platform-release/global/images/common-cpu-v20240922
+    ray_worker_small:
+        min_workers: 0
+        resources: {"CPU": 2}
+        node_config:
+            machineType: n1-standard-2
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  sourceImage: projects/deeplearning-platform-release/global/images/common-cpu-v20240922
+            scheduling:
+              - preemptible: true

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

@@ -0,0 +1,8 @@
+auth:
+  ssh_user: ubuntu
+cluster_name: minimal
+provider:
+  availability_zone: us-west1-a
+  project_id: null # TODO: set your GCP project ID here
+  region: us-west1
+  type: gcp

python/ray/autoscaler/gcp/example-tpu-pod-topology.yaml

@@ -0,0 +1,58 @@
+# This example demonstrates how to schedule TPU pods using `acceleratorConfig`, i.e.
+# a combination of the chip and underlying topology.
+# See https://cloud.google.com/tpu/docs/supported-tpu-configurations for more details.
+# A unique identifier for the head node and workers of this cluster.
+cluster_name: tputopology
+
+max_workers: 2
+
+available_node_types:
+    ray_head_default:
+        min_workers: 0
+        max_workers: 0
+        resources: {"CPU": 0}
+        # Provider-specific config for this node type, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-4
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/ubuntu-os-cloud/global/images/family/ubuntu-2004-lts
+    ray_tpu:
+        min_workers: 1
+        max_workers: 1
+        resources: {"TPU": 1}  # use TPU custom resource in your code
+        node_config:
+            # Defining the accelerator configuration, including the:
+            # - type (in this case a V4) and
+            # - topology 2x2x1 will create a v4-8.
+            acceleratorConfig:
+              type: V4
+              topology: 2x2x1
+            runtimeVersion: tpu-vm-v4-base
+
+provider:
+    type: gcp
+    region: us-central2
+    availability_zone: us-central2-b
+    project_id: null # Replace this with your GCP project ID.
+
+initialization_commands:
+  - sudo apt-get update
+  - sudo apt-get install -y python3-pip python-is-python3
+
+setup_commands:
+  - pip install 'ray[default]'
+
+head_setup_commands:
+  - pip install google-api-python-client
+
+# Specify the node type of the head node (as configured above).
+head_node_type: ray_head_default

python/ray/autoscaler/gcp/example-tpu-pod.yaml

@@ -0,0 +1,54 @@
+# A unique identifier for the head node and workers of this cluster.
+cluster_name: tpupodtest
+
+max_workers: 2
+
+available_node_types:
+    ray_head_default:
+        min_workers: 0
+        max_workers: 0
+        resources: {"CPU": 0}
+        # Provider-specific config for this node type, e.g. instance type. By default
+        # Ray will auto-configure unspecified fields such as subnets and ssh-keys.
+        # For more documentation on available fields, see:
+        # https://cloud.google.com/compute/docs/reference/rest/v1/instances/insert
+        node_config:
+            machineType: n1-standard-4
+            disks:
+              - boot: true
+                autoDelete: true
+                type: PERSISTENT
+                initializeParams:
+                  diskSizeGb: 50
+                  # See https://cloud.google.com/compute/docs/images for more images
+                  sourceImage: projects/ubuntu-os-cloud/global/images/family/ubuntu-2004-lts
+    ray_tpu:
+        min_workers: 1
+        max_workers: 1
+        resources: {"TPU": 1}  # use TPU custom resource in your code
+        node_config:
+            # Note: A v4-16 will have 2 hosts.
+            # While the cluster launcher can create multiple TPU pods, note that
+            # "proper" autoscaling currently does not work as expected as all hosts
+            # in a TPU pod need to execute the same program.
+            acceleratorType: v4-16
+            runtimeVersion: tpu-vm-v4-base
+
+provider:
+    type: gcp
+    region: us-central2
+    availability_zone: us-central2-b
+    project_id: null # Replace this with your GCP project ID.
+
+initialization_commands:
+  - sudo apt-get update
+  - sudo apt-get install -y python3-pip python-is-python3
+
+setup_commands:
+  - pip install 'ray[default]'
+
+head_setup_commands:
+  - pip install google-api-python-client
+
+# Specify the node type of the head node (as configured above).
+head_node_type: ray_head_default

python/ray/autoscaler/gcp/tests/gce_config.yaml

@@ -0,0 +1,13 @@
+base_image: {{ env["RAY_IMAGE_NIGHTLY_CPU"] | default("anyscale/ray:nightly-py39") }}
+debian_packages: []
+env_vars:
+  RAY_WHEEL_URL: {{ env["RAY_WHEELS"] | default("") }}
+
+python:
+  pip_packages: []
+  conda_packages: []
+
+post_build_cmds:
+  - pip3 uninstall -y ray && pip3 install -U {{ env["RAY_WHEELS"] | default("ray") }}
+  - pip3 install -U ray[default]
+  - {{ env["RAY_WHEELS_SANITY_CHECK"] | default("echo No Ray wheels sanity check") }}

python/ray/autoscaler/gcp/tests/single_node_32_cpu_gce.yaml

@@ -0,0 +1,27 @@
+cloud_id: {{env["ANYSCALE_CLOUD_ID"]}}
+region: us-west1
+allowed_azs:
+    - us-west1-c
+
+max_workers: 0
+
+head_node_type:
+    name: head_node
+    instance_type: n2-standard-32 # m5.8xlarge
+
+worker_node_types: []
+
+gcp_advanced_configurations_json:
+  instance_properties:
+    disks:
+      - boot: true
+        auto_delete: true
+        initialize_params:
+          disk_size_gb: 500
+
+#advanced_configurations_json:
+#    BlockDeviceMappings:
+#        - DeviceName: /dev/sda1
+#          Ebs:
+#            DeleteOnTermination: true
+#            VolumeSize: 500

python/ray/autoscaler/gcp/tpu.yaml

@@ -0,0 +1,39 @@
+# A unique identifier for the head node and workers of this cluster.
+cluster_name: tputest
+
+# The maximum number of worker nodes to launch in addition to the head node.
+max_workers: 7
+
+available_node_types:
+    ray_head_default:
+        resources: {"TPU": 1}  # use TPU custom resource in your code
+        node_config:
+            # Only v2-8, v3-8 and v4-8 accelerator types are currently supported.
+            # Support for TPU pods will be added in the future.
+            acceleratorType: v2-8
+            runtimeVersion: v2-alpha
+            schedulingConfig:
+                # Set to false to use non-preemptible TPUs
+                preemptible: false
+    ray_tpu:
+        min_workers: 1
+        resources: {"TPU": 1}  # use TPU custom resource in your code
+        node_config:
+            acceleratorType: v2-8
+            runtimeVersion: v2-alpha
+            schedulingConfig:
+                preemptible: true
+
+provider:
+    type: gcp
+    region: us-central1
+    availability_zone: us-central1-b
+    project_id: null # Replace this with your GCP project ID.
+
+setup_commands:
+  - sudo apt install python-is-python3 -y
+  - pip3 install --upgrade pip
+  - pip3 install -U "ray[default]"
+
+# Specify the node type of the head node (as configured above).
+head_node_type: ray_head_default