Interface ProductionVariant

All Superinterfaces:
All Known Implementing Classes:

@Generated(value="jsii-pacmak/1.84.0 (build 5404dcf)", date="2023-06-19T16:30:48.125Z") @Stability(Stable) public interface ProductionVariant extends
Identifies a model that you want to host and the resources to deploy for hosting it.


 // The code below shows an example of how to instantiate this type.
 // The values are placeholders you should change.
 AcceleratorType acceleratorType;
 InstanceType instanceType;
 ProductionVariant productionVariant = ProductionVariant.builder()
         // the properties below are optional

See Also:
  • Method Details

    • getInstanceType

      @Stability(Stable) @NotNull InstanceType getInstanceType()
      The ML compute instance type.
    • getModelName

      @Stability(Stable) @NotNull String getModelName()
      The name of the model that you want to host.

      This is the name that you specified when creating the model.

    • getVariantName

      @Stability(Stable) @NotNull String getVariantName()
      The name of the production variant.
    • getAcceleratorType

      @Stability(Stable) @Nullable default AcceleratorType getAcceleratorType()
      The size of the Elastic Inference (EI) instance to use for the production variant.

      Default: - None

    • getInitialInstanceCount

      @Stability(Stable) @Nullable default Number getInitialInstanceCount()
      Number of instances to launch initially.

      Default: - 1

    • getInitialVariantWeight

      @Stability(Stable) @Nullable default Number getInitialVariantWeight()
      Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.

      Default: - 1.0

    • builder

      @Stability(Stable) static ProductionVariant.Builder builder()
      a ProductionVariant.Builder of ProductionVariant