aws-cdk-lib.aws_stepfunctions_tasks.ProductionVariant

ProductionVariant Struct

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

Source

aws-stepfunctions-tasks/lib/sagemaker/base-types.ts

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_ec2 as ec2 } from 'aws-cdk-lib';
import { aws_stepfunctions_tasks as stepfunctions_tasks } from 'aws-cdk-lib';

declare const acceleratorType: stepfunctions_tasks.AcceleratorType;
declare const instanceType: ec2.InstanceType;
const productionVariant: stepfunctions_tasks.ProductionVariant = {
  instanceType: instanceType,
  modelName: 'modelName',
  variantName: 'variantName',

  // the properties below are optional
  acceleratorType: acceleratorType,
  initialInstanceCount: 123,
  initialVariantWeight: 123,
};

Properties

acceleratorType?optionalAcceleratorTypeaccelerator_type?optionalAcceleratorTypeacceleratorType?optionalAcceleratorTypeAcceleratorType?optionalAcceleratorTypeAcceleratorType?optionalAcceleratorType= None#

The size of the Elastic Inference (EI) instance to use for the production variant.

initialInstanceCount?optionalnumberinitial_instance_count?optionalint | floatinitialInstanceCount?optionalNumberInitialInstanceCount?optionaldoubleInitialInstanceCount?optional*float64= 1#

Number of instances to launch initially.

initialVariantWeight?optionalnumberinitial_variant_weight?optionalint | floatinitialVariantWeight?optionalNumberInitialVariantWeight?optionaldoubleInitialVariantWeight?optional*float64= 1.0#

Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.

instanceTypeInstanceTypeinstance_typeInstanceTypeinstanceTypeInstanceTypeInstanceTypeInstanceTypeInstanceTypeInstanceTyperequired#

The ML compute instance type.

modelNamestringmodel_namestrmodelNameStringModelNamestringModelName*stringrequired#

The name of the model that you want to host.

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

variantNamestringvariant_namestrvariantNameStringVariantNamestringVariantName*stringrequired#

The name of the production variant.