SageMaker endpoint production variants should have an initial instance count greater than 1

How to fix it

• Replaces the resource: An endpoint configuration cannot be edited: create a new one, update each endpoint to it and wait for InService, then delete this one.

In the console

SageMaker Studio → Models → Deploy → Initial instance count, which writes a new endpoint configuration

Initial instance count

2 or more for every instance-based variant

Endpoint name

Each existing endpoint that uses this configuration, so it moves to the new one

With the AWS CLI

aws sagemaker create-endpoint-config --endpoint-config-name <endpoint-config-name> --production-variants '[{"VariantName":"<variant-name>","ModelName":"<model-name>","InstanceType":"<instance-type>","InitialInstanceCount":2}]' --region <region>

With Terraform

resource "aws_sagemaker_endpoint_configuration" "this" {
  production_variants {
    variant_name           = var.variant_name
    model_name             = var.model_name
    instance_type          = var.instance_type
    initial_instance_count = 2
  }
}