mirror of
https://github.com/vale981/ray
synced 2025-03-07 02:51:39 -05:00
92 lines
3.1 KiB
YAML
92 lines
3.1 KiB
YAML
# This file is generated by `ray project create`.
|
|
|
|
# A unique identifier for the head node and workers of this cluster.
|
|
cluster_name: horovod-release-tests
|
|
|
|
# The minimum number of workers nodes to launch in addition to the head
|
|
# node. This number should be >= 0.
|
|
min_workers: 3
|
|
# The maximum number of workers nodes to launch in addition to the head
|
|
# node. This takes precedence over min_workers. min_workers defaults to 0.
|
|
max_workers: 3
|
|
|
|
# If a node is idle for this many minutes, it will be removed.
|
|
idle_timeout_minutes: 5
|
|
|
|
# Cloud-provider specific configuration.
|
|
provider:
|
|
type: aws
|
|
region: us-west-2
|
|
availability_zone: us-west-2a
|
|
cache_stopped_nodes: False
|
|
|
|
# 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.
|
|
# ssh_private_key: /path/to/your/key.pem
|
|
available_node_types:
|
|
gpu_2_32:
|
|
min_workers: 3
|
|
max_workers: 3
|
|
resources: {"CPU": 32, "GPU": 2}
|
|
node_config:
|
|
InstanceType: g3.8xlarge
|
|
ImageId: ami-0a2363a9cff180a64
|
|
BlockDeviceMappings:
|
|
- DeviceName: /dev/sda1
|
|
Ebs:
|
|
VolumeSize: 150
|
|
TagSpecifications:
|
|
- ResourceType: "instance"
|
|
Tags:
|
|
- Key: anyscale-user
|
|
Value: '{{env["ANYSCALE_USER"]}}'
|
|
- Key: anyscale-expiration
|
|
Value: '{{env["ANSYCALE_EXPIRATION"]}}'
|
|
|
|
# Provider-specific config for the head node, e.g. instance type. By default
|
|
# Ray will auto-configure unspecified fields such as SubnetId and KeyName.
|
|
# For more documentation on available fields, see:
|
|
# http://boto3.readthedocs.io/en/latest/reference/services/ec2.html#EC2.ServiceResource.create_instances
|
|
head_node:
|
|
InstanceType: g3.8xlarge
|
|
ImageId: latest_dlami
|
|
BlockDeviceMappings:
|
|
- DeviceName: /dev/sda1
|
|
Ebs:
|
|
VolumeSize: 150
|
|
|
|
worker_nodes:
|
|
InstanceType: g3.8xlarge
|
|
ImageId: latest_dlami
|
|
BlockDeviceMappings:
|
|
- DeviceName: /dev/sda1
|
|
Ebs:
|
|
VolumeSize: 150
|
|
InstanceMarketOptions:
|
|
MarketType: spot
|
|
|
|
|
|
file_mounts: {}
|
|
|
|
setup_commands:
|
|
- pip install -U {{env["RAY_WHEEL"]}}
|
|
- pip install 'ray[rllib]'
|
|
- pip install torch torchvision
|
|
- HOROVOD_WITH_GLOO=1 HOROVOD_WITHOUT_MPI=1 HOROVOD_WITHOUT_TENSORFLOW=1 HOROVOD_WITHOUT_MXNET=1 HOROVOD_WITH_PYTORCH=1 pip install -U git+https://github.com/horovod/horovod.git
|
|
|
|
# Command to start ray on the head node. You don't need to change this.
|
|
head_start_ray_commands:
|
|
- ray stop
|
|
- export RAY_BACKEND_LOG_LEVEL=debug
|
|
- 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
|
|
- export RAY_BACKEND_LOG_LEVEL=debug
|
|
- ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
|