translator-example-cluster.yaml

# EKS cluster name for cortex (default: cortex)
cluster_name: cortex

# AWS region
region: us-east-1

# instance type
instance_type: g4dn.xlarge

# minimum number of instances (must be >= 0)
min_instances: 1

# maximum number of instances (must be >= 1)
max_instances: 10

# whether to disable API gateway cluster-wide
# if set to "public" (the default), each API can specify whether to use API Gateway
# if set to "none", no APIs will be allowed to use API Gateway
api_gateway: none  # must be "public" or "none"

spot: true

spot_config:
  # additional instances with identical or better specs than the primary instance type (defaults to only the primary instance)
  instance_distribution: [g4dn.2xlarge]

  # minimum number of on demand instances (default: 0)
  on_demand_base_capacity: 0

  # percentage of on demand instances to use after the on demand base capacity has been met [0, 100] (default: 50)
  # note: setting this to 0 may hinder cluster scale up when spot instances are not available
  on_demand_percentage_above_base_capacity: 50

  # fallback to on-demand instances if spot instances were unable to be allocated (default: true)
  on_demand_backup: true