mirror of
https://github.com/wassname/ray.git
synced 2026-07-01 04:50:40 +08:00
Barak Michener
05c4e3fb2a
* necessary changes * Split bazel install * manylinux2014 * change references to manylinux2014 * Fix lint * port alex's docker build changes * fix config issue * remove extra manylinux2010 requirement script * revert SHA overwrite * wip * incompatible_linklibs * fix nits
99 lines
3.8 KiB
YAML
99 lines
3.8 KiB
YAML
# An unique identifier for the head node and workers of this cluster.
|
|
cluster_name: gpu-docker
|
|
|
|
# The minimum number of workers nodes to launch in addition to the head
|
|
# node. This number should be >= 0.
|
|
min_workers: 0
|
|
|
|
# The maximum number of workers nodes to launch in addition to the head
|
|
# node. This takes precedence over min_workers.
|
|
max_workers: 2
|
|
|
|
# The initial number of worker nodes to launch in addition to the head
|
|
# node. When the cluster is first brought up (or when it is refreshed with a
|
|
# subsequent `ray up`) this number of nodes will be started.
|
|
initial_workers: 0
|
|
|
|
# Whether or not to autoscale aggressively. If this is enabled, if at any point
|
|
# we would start more workers, we start at least enough to bring us to
|
|
# initial_workers.
|
|
autoscaling_mode: default
|
|
|
|
# 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"
|
|
container_name: "ray_nvidia_docker" # e.g. ray_docker
|
|
|
|
# # Example of running a GPU head with CPU workers
|
|
# head_image: "rayproject/ray:latest-gpu"
|
|
|
|
# worker_image: "rayproject/ray:latest"
|
|
|
|
# The autoscaler will scale up the cluster to this target fraction of resource
|
|
# usage. For example, if a cluster of 10 nodes is 100% busy and
|
|
# target_utilization is 0.8, it would resize the cluster to 13. This fraction
|
|
# can be decreased to increase the aggressiveness of upscaling.
|
|
# This value must be less than 1.0 for scaling to happen.
|
|
target_utilization_fraction: 0.8
|
|
|
|
# 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
|
|
|
|
# How Ray will authenticate with newly launched nodes.
|
|
auth:
|
|
ssh_user: ubuntu
|
|
# you must specify paths to matching private and public key pair files
|
|
# use `ssh-keygen -t rsa -b 4096` to generate a new ssh key pair
|
|
ssh_private_key: ~/.ssh/id_rsa
|
|
# changes to this should match what is specified in file_mounts
|
|
ssh_public_key: ~/.ssh/id_rsa.pub
|
|
|
|
# Provider-specific config for the head node, e.g. instance type. By default
|
|
# Ray will auto-configure unspecified fields using defaults.yaml
|
|
head_node:
|
|
azure_arm_parameters:
|
|
vmSize: Standard_NC6s_v3
|
|
|
|
# Provider-specific config for worker nodes, e.g. instance type. By default
|
|
# Ray will auto-configure unspecified fields using defaults.yaml
|
|
worker_nodes:
|
|
azure_arm_parameters:
|
|
vmSize: Standard_NC6s_v3
|
|
|
|
# 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",
|
|
"/home/ubuntu/.ssh/id_rsa.pub": "~/.ssh/id_rsa.pub"
|
|
}
|
|
|
|
# List of shell commands to run to set up nodes.
|
|
# NOTE: rayproject/ray:latest has ray latest bundled
|
|
setup_commands: []
|
|
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-1.1.0.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 azure-cli-core==2.4.0 azure-mgmt-compute==12.0.0 azure-mgmt-msi==1.0.0 azure-mgmt-network==10.1.0
|
|
|
|
# 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
|