ray/release/nightly_tests/dataset/ray_sgd_training_compute.yaml
Chen Shen 107aef89a8
[CUJ2] add nightly tests for running 500GB ray train (#20195)
* add

* update cluster env

* fix build

Co-authored-by: Matthew Deng <matthew.j.deng@gmail.com>
2021-11-21 20:04:45 -08:00

31 lines
621 B
YAML

cloud_id: cld_17WvYIBBkdgLwEUNcLeRAE
region: us-west-2
allowed_azs:
- us-west-2a
max_workers: 65
aws:
IamInstanceProfile: {"Name": "ray-autoscaler-v1"}
BlockDeviceMappings:
- DeviceName: /dev/sda1
Ebs:
VolumeSize: 500
head_node_type:
name: head_node
instance_type: i3.8xlarge
worker_node_types:
- name: memory_node
instance_type: i3.8xlarge
min_workers: 49
max_workers: 49
use_spot: false
- name: gpu_node
instance_type: g4dn.xlarge
min_workers: 16
max_workers: 16
use_spot: false
resources:
cpu: 0