mirror of
https://github.com/wassname/ray.git
synced 2026-07-05 16:44:54 +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
114 lines
4.8 KiB
YAML
114 lines
4.8 KiB
YAML
# An unique identifier for the head node and workers of this cluster.
|
|
cluster_name: default
|
|
|
|
## NOTE: Typically for local clusters, min_workers == initial_workers == max_workers == len(worker_ips).
|
|
|
|
# The minimum number of workers nodes to launch in addition to the head
|
|
# node. This number should be >= 0.
|
|
# Typically, min_workers == initial_workers == max_workers == len(worker_ips).
|
|
min_workers: 0
|
|
# The initial number of worker nodes to launch in addition to the head node.
|
|
# Typically, min_workers == initial_workers == max_workers == len(worker_ips).
|
|
initial_workers: 0
|
|
|
|
# The maximum number of workers nodes to launch in addition to the head node.
|
|
# This takes precedence over min_workers.
|
|
# Typically, min_workers == initial_workers == max_workers == len(worker_ips).
|
|
max_workers: 0
|
|
|
|
# Autoscaling parameters.
|
|
# Ignore this if min_workers == initial_workers == max_workers.
|
|
autoscaling_mode: default
|
|
target_utilization_fraction: 0.8
|
|
idle_timeout_minutes: 5
|
|
|
|
# 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. Assumes Docker is installed.
|
|
docker:
|
|
image: "rayproject/ray:latest-gpu" # You can change this to latest-cpu if you don't need GPU support and want a faster startup
|
|
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"
|
|
|
|
# Local specific configuration.
|
|
provider:
|
|
type: local
|
|
head_ip: YOUR_HEAD_NODE_HOSTNAME
|
|
worker_ips: [WORKER_NODE_1_HOSTNAME, WORKER_NODE_2_HOSTNAME, ... ]
|
|
# Optional when running automatic cluster management on prem. If you use a coordinator server,
|
|
# then you can launch multiple autoscaling clusters on the same set of machines, and the coordinator
|
|
# will assign individual nodes to clusters as needed.
|
|
# coordinator_address: "<host>:<port>"
|
|
|
|
# How Ray will authenticate with newly launched nodes.
|
|
auth:
|
|
ssh_user: YOUR_USERNAME
|
|
# Optional if an ssh private key is necessary to ssh to the cluster.
|
|
# ssh_private_key: ~/.ssh/id_rsa
|
|
|
|
# Leave this empty.
|
|
head_node: {}
|
|
|
|
# Leave this empty.
|
|
worker_nodes: {}
|
|
|
|
# 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 each 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).
|
|
# Uncomment the following line if you want to run the nightly version of ray (as opposed to the latest)
|
|
# - 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: []
|
|
|
|
# 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 -c unlimited && ray start --head --port=6379 --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
|