Package software.amazon.awscdk.services.sagemaker.alpha

Interface InstanceProductionVariantProps

All Superinterfaces:
software.amazon.jsii.JsiiSerializable
All Known Implementing Classes:
InstanceProductionVariantProps.Jsii$Proxy
@Generated(value="jsii-pacmak/1.125.0 (build fdbe357)", date="2026-01-23T11:19:58.541Z") @Stability(Experimental) public interface InstanceProductionVariantProps extends software.amazon.jsii.JsiiSerializable
(experimental) Construction properties for an instance production variant.

Example: 

 // The code below shows an example of how to instantiate this type.
 // The values are placeholders you should change.
 import software.amazon.awscdk.services.sagemaker.alpha.*;
 import software.amazon.awscdk.*;
 AcceleratorType acceleratorType;
 InstanceType instanceType;
 Model model;
 InstanceProductionVariantProps instanceProductionVariantProps = InstanceProductionVariantProps.builder()
         .model(model)
         .variantName("variantName")
         // the properties below are optional
         .acceleratorType(acceleratorType)
         .containerStartupHealthCheckTimeout(Duration.minutes(30))
         .initialInstanceCount(123)
         .initialVariantWeight(123)
         .instanceType(instanceType)
         .build();

  • Method Details

    • getModel

      @Stability(Experimental) @NotNull IModel getModel()
      (experimental) The model to host.

    • getVariantName

      @Stability(Experimental) @NotNull String getVariantName()
      (experimental) Name of the production variant.

    • getAcceleratorType

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

      EI instances provide on-demand GPU computing for inference.

      Default: - none

    • getContainerStartupHealthCheckTimeout

      @Stability(Experimental) @Nullable default Duration getContainerStartupHealthCheckTimeout()
      (experimental) The timeout value, in seconds, for your inference container to pass health check.

      Range between 60 and 3600 seconds.

      Default: - none

    • getInitialInstanceCount

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

      Default: 1

    • getInitialVariantWeight

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

      The traffic to a production variant is determined by the ratio of the variant weight to the sum of all variant weight values across all production variants.

      Default: 1.0

    • getInstanceType

      @Stability(Experimental) @Nullable default InstanceType getInstanceType()
      (experimental) Instance type of the production variant.

      Default: InstanceType.T2_MEDIUM

    • builder

      @Stability(Experimental) static InstanceProductionVariantProps.Builder builder()
      Returns:
      a InstanceProductionVariantProps.Builder of InstanceProductionVariantProps