capabilities.work

Deploy Existing Model

A 4-step recipe with Amazon SageMaker. We can help you get access.

Recipe · 4 steps

Deploy Existing Model

with Amazon SageMaker · Artificial Intelligence Management

Stand up an endpoint for a model that already exists.

  1. Describe the model to confirm it exists and capture its ARN before building an endpoint configuration around it.
  2. Define an endpoint configuration that places the existing model on a single production variant with the requested instance type and count.
  3. Create a hosted endpoint from the endpoint configuration so SageMaker provisions resources and deploys the model.
  4. Describe the endpoint and loop while it remains in the Creating state, continuing once it reaches a terminal state.
What you'll need to have ready
  • modelName: The name of the existing model to deploy.
  • endpointConfigName: A unique name for the endpoint configuration.
  • variantName: The name of the production variant.
  • initialInstanceCount: The initial number of instances to launch for the variant.
  • instanceType: The ML compute instance type to deploy for the variant.
  • endpointName: A unique name for the endpoint.
For your developer

Arazzo workflow amazon-sagemaker:deploy-existing-model, 4 operations: DescribeModel → CreateEndpointConfig → CreateEndpoint → DescribeEndpoint. Specs on APIs.io.

More recipes with Amazon SageMaker

Audit Endpoint FleetDeploy Model to EndpointInventory ModelsProvision Notebook InstanceRegister Latest Completed TrainingTrain Model and Poll JobTrain Then Deploy