Legacy YAML Config

Using yaml config files to configure Cortex deployments easily and quickly

Introduction

This document is for users who have been using Cerebrium for a while and are familiar with the legacy YAML config file format. If you are new to Cerebrium, please refer to the initial setup guide.

Your legacy YAML config file can be converted to a toml config file by answering yes to the prompt when you run cerebrium deploy as normal. This will create a cerebrium.toml file in your project directory which you can then edit as you wish. Additionally, all the dependencies in your pkglist.txt and conda_pkglist.txt files will be added to the cerebrium.toml file automatically

Legacy Folder Structure

Cortex supports the use of config YAML files to configure various aspects of your project such as hardware requirements, memory and much more. Using config files makes it easier to keep track of your Cerebrium deployments, share them and use git versioning to show changes over time.

project_name/
├── main.py
├── requirements.txt
├── pkglist.txt
├── conda_pkglist.txt
└── config.yaml

To deploy your model with a specific config file, you can use the cerebrium deploy command with the --config-file flag to specify the path to your config file. Otherwise cerebrium deploy will use the config.yaml (if there is no cerebrium.toml) in the file directory.
Your config file can be named anything you want and can be placed anywhere on your local machine. However, remember to use the cerebrium deploy command in the same directory as your main.py as you would normally.

Deploying your model with a config file is as simple as:

cerebrium deploy

Config File Format and Parameters

The parameters for your config file are the same as those which you would use as flags for a normal cerebrium deploy command. They’re tabulated below for your convenience:

Parameter	Description	Type	Default
name	Name of the deployment	string
api_key	API key for the deployment	string	not included for safety
hardware	Hardware to use for the deployment	string	GPU
gpu_count	The number of GPUs to specify	int	2
cpu	The number of CPU cores to use	int	2
memory	The amount of Memory to use in GB	int	14.5
log_level	Log level for the deployment	string	INFO
include	Local files to include in the deployment	string	’[./*, main.py, requirements.txt, pkglist.txt, conda_pkglist.txt]‘
exclude	Local Files to exclude from the deployment	string	’[./., ./__]‘
disable_animation	Whether to disable the animation in the logs.	boolean	false
python_version	The Python version you would like to run	float	3.9
min_replicas	The minimum number of replicas to run.	int	0
max_replicas	The maximum number of replicas to scale to.	int	*plan limit
cooldown	The number of seconds to keep your model warm after each request. It resets after every request	int	60

Config File Example

%YAML 1.2
---
name: an-optional-name
api_key: an-optional-api-key
hardware: GPU
exclude: "[./.*, ./__*]"
include: "[./*, main.py, requirements.txt, pkglist.txt, conda_pkglist.txt]"
log_level: INFO
disable_animation: false
python_version: 3.9
min_replicas: 0
max_replicas: 30