wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-10 14:28:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

autoscaler yaml for long running distributed

Browse Source
This commit is contained in:
Alex
2021-02-05 19:40:02 +00:00
parent 75886c8e78
commit 5f61ace191
1 changed files with 4 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
release/long_running_distributed_tests/autoscaler-cluster.yaml
+4 -10
View File
@@ -5,11 +5,6 @@ max_workers: 3
idle_timeout_minutes: 15
docker:
image: rayproject/ray-ml:1.2.0-gpu
container_name: ray_container
pull_before_run: True
provider:
type: aws
region: us-west-2
@@ -21,17 +16,16 @@ auth:
head_node:
InstanceType: g3.8xlarge
ImageId: ami-0828a1066dc750737
ImageId: ami-0b1a80ce62c464a55
worker_nodes:
InstanceType: g3.8xlarge
ImageId: ami-0828a1066dc750737
InstanceMarketOptions:
MarketType: spot
ImageId: ami-0b1a80ce62c464a55
setup_commands:
- sudo apt-get install -y libglib2.0-0 libcudnn7=7.6.5.32-1+cuda10.1
# - 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/1.2.0/4c71f76b25bde02f208bfb21451347834994a72a/ray-1.2.0-cp37-cp37m-manylinux2014_x86_64.whl
- pip install torch==1.4.0 torchvision==0.5.0 ray[all]
# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands: