Package software.amazon.awscdk.services.stepfunctions.tasks

Interface ProductionVariant

All Superinterfaces:

software.amazon.jsii.JsiiSerializable

All Known Implementing Classes:

ProductionVariant.Jsii$Proxy

@Generated(value="jsii-pacmak/1.116.0 (build 0eddcff)",
           date="2025-10-24T13:34:48.330Z")
@Stability(Stable)
public interface ProductionVariant
extends software.amazon.jsii.JsiiSerializable

Identifies a model that you want to host and the resources to deploy for hosting it.

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.ec2.*;
 import software.amazon.awscdk.services.stepfunctions.tasks.*;
 AcceleratorType acceleratorType;
 InstanceType instanceType;
 ProductionVariant productionVariant = ProductionVariant.builder()
         .instanceType(instanceType)
         .modelName("modelName")
         .variantName("variantName")
         // the properties below are optional
         .acceleratorType(acceleratorType)
         .initialInstanceCount(123)
         .initialVariantWeight(123)
         .build();
 

See Also:

• https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_ProductionVariant.html

Nested Class Summary

Nested Classes

Modifier and Type	Interface	Description
static final class	ProductionVariant.Builder	A builder for ProductionVariant
static final class	ProductionVariant.Jsii$Proxy	An implementation for ProductionVariant

Method Summary

Modifier and Type	Method	Description
static ProductionVariant.Builder	builder()
default AcceleratorType	getAcceleratorType()	The size of the Elastic Inference (EI) instance to use for the production variant.
default Number	getInitialInstanceCount()	Number of instances to launch initially.
default Number	getInitialVariantWeight()	Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
InstanceType	getInstanceType()	The ML compute instance type.
String	getModelName()	The name of the model that you want to host.
String	getVariantName()	The name of the production variant.

Methods inherited from interface software.amazon.jsii.JsiiSerializable

$jsii$toJson

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()

Returns:

a ProductionVariant.Builder of ProductionVariant