Files
ray/release/rllib_tests/regression_tests/cluster.yaml
T
2021-01-30 04:32:18 +00:00

46 lines
1.4 KiB
YAML

cluster_name: ray-rllib-regression-tests
min_workers: 0
max_workers: 0
docker:
image: anyscale/ray-ml:latest-gpu
container_name: ray_container
pull_before_run: True
# 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
head_node:
InstanceType: p3.16xlarge
ImageId: latest_dlami
file_mounts:
/compact-regression-tests-torch.yaml: compact-regression-tests-torch.yaml
/compact-regression-tests-tf.yaml: compact-regression-tests-tf.yaml
/run.sh: run.sh
# List of shell commands to run to set up nodes.
setup_commands:
- sudo apt-get install -y libglib2.0-0 libcudnn7=7.6.5.32-1+cuda10.1
- pip install -U https://ray-wheels.s3-us-west-2.amazonaws.com/releases/1.2.0/b4d87b8fc5ff03b868adba35b37da32b7be9f71f/ray-1.2.0-cp37-cp37m-manylinux2014_x86_64.whl
# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
- ray stop
- ulimit -n 65536; OMP_NUM_THREADS=1 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; OMP_NUM_THREADS=1 ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076