Creates an endpoint configuration that Amazon SageMaker hosting services uses to deploy
models. In the configuration, you identify one or more models, created using the
Use this API only if you want to use Amazon SageMaker hosting services to deploy
models into production.
API, to deploy and the resources that you want Amazon SageMaker to provision. Then
you call the CreateEndpoint
Use this API only if you want to use Amazon SageMaker hosting services to deploy models into production.
In the request, you define one or more
ProductionVariants, each of which
identifies a model. Each
ProductionVariant parameter also describes the
resources that you want Amazon SageMaker to provision. This includes the number and
type of ML compute instances to deploy.
If you are hosting multiple models, you also assign a
specify how much traffic you want to allocate to each model. For example, suppose
that you want to host two models, A and B, and you assign traffic weight 2 for model
A and 1 for model B. Amazon SageMaker distributes two-thirds of the traffic to Model
A, and one-third to model B.
For .NET Core and PCL this operation is only available in asynchronous form. Please refer to CreateEndpointConfigAsync.
public abstract CreateEndpointConfigResponse CreateEndpointConfig( CreateEndpointConfigRequest request )
Container for the necessary parameters to execute the CreateEndpointConfig service method.
|ResourceLimitExceededException||You have exceeded an Amazon SageMaker resource limit. For example, you might have too many training jobs created.|
Supported in: 4.5, 4.0, 3.5
Supported in: Windows Store Apps
Supported in: Windows Phone 8.1
Supported in: Xamarin Android
Supported in: Xamarin iOS (Unified)
Supported in: Xamarin.Forms