Files
ray/python/ray/tune/examples/cluster-p3.yaml
T
krfricke 619e44e54a [tune] Added WandbLogger (#9725)
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
Co-authored-by: Kai Fricke <kai@anyscale.com>
2020-07-30 13:09:03 -07:00

72 lines
2.1 KiB
YAML

# An unique identifier for the head node and workers of this cluster.
cluster_name: sgd-pytorch
# The maximum number of workers nodes to launch in addition to the head
# node. This takes precedence over min_workers. min_workers default to 0.
min_workers: 0
initial_workers: 0
max_workers: 0
target_utilization_fraction: 0.9
# If a node is idle for this many minutes, it will be removed.
idle_timeout_minutes: 20
# docker:
# image: tensorflow/tensorflow:1.5.0-py3
# container_name: ray_docker
# Cloud-provider specific configuration.
provider:
type: aws
region: us-west-2
# How Ray will authenticate with newly launched nodes.
auth:
ssh_user: ubuntu
head_node:
InstanceType: p3.8xlarge
ImageId: latest_dlami
InstanceMarketOptions:
MarketType: spot
# SpotOptions:
# MaxPrice: "9.0"
worker_nodes:
InstanceType: p3.8xlarge
ImageId: latest_dlami
# Run workers on spot by default. Comment this out to use on-demand.
InstanceMarketOptions:
MarketType: spot
# SpotOptions:
# MaxPrice: "9.0"
setup_commands:
- ray || pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp36-cp36m-manylinux1_x86_64.whl
- pip install -U ipdb ray[rllib] torch torchvision
# Install apex.
# - rm -rf apex || true
# - git clone https://github.com/NVIDIA/apex && cd apex && pip install -v --no-cache-dir ./ || true
file_mounts: {
}
# 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
- ray start --head --redis-port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml --object-store-memory=1000000000
# 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 --object-store-memory=1000000000