cluster_name: ray-rllib-regression-tests min_workers: 0 max_workers: 0 # 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: ami-07728e9e2742b0662 # Deep Learning AMI (Ubuntu 16.04) # Set primary volume to 25 GiB BlockDeviceMappings: - DeviceName: /dev/sda1 Ebs: VolumeSize: 100 # List of shell commands to run to set up nodes. setup_commands: - wget --quiet https://s3-us-west-2.amazonaws.com/ray-wheels/{{ray_branch}}/{{commit}}/ray-{{ray_version}}-cp36-cp36m-manylinux1_x86_64.whl - conda uninstall -y terminado - source activate tensorflow_p36 && pip install -U ray-{{ray_version}}-cp36-cp36m-manylinux1_x86_64.whl - source activate tensorflow_p36 && pip install ray[rllib] ray[debug] - source activate tensorflow_p36 && pip install boto3==1.4.8 cython==0.29.0 # Command to start ray on the head node. You don't need to change this. head_start_ray_commands: - source activate tensorflow_p36 && ray stop - ulimit -n 65536; source activate tensorflow_p36 && OMP_NUM_THREADS=1 ray start --head --redis-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: - source activate tensorflow_p36 && ray stop - ulimit -n 65536; source activate tensorflow_p36 && OMP_NUM_THREADS=1 ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076