Experimental
@aws-cdk/aws-sagemaker-alpha is an experimental (alpha) package: its API may change in any release, without a major version bump.
InstanceProductionVariantProps Struct
Construction properties for an instance production variant.
Example
ts
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import * as sagemaker_alpha from '@aws-cdk/aws-sagemaker-alpha';
import * as cdk from 'aws-cdk-lib';
declare const acceleratorType: sagemaker_alpha.AcceleratorType;
declare const instanceType: sagemaker_alpha.InstanceType;
declare const model: sagemaker_alpha.Model;
const instanceProductionVariantProps: sagemaker_alpha.InstanceProductionVariantProps = {
model: model,
variantName: 'variantName',
// the properties below are optional
acceleratorType: acceleratorType,
containerStartupHealthCheckTimeout: cdk.Duration.minutes(30),
initialInstanceCount: 123,
initialVariantWeight: 123,
instanceType: instanceType,
};
Properties
acceleratorTypeAcceleratorTypeaccelerator_typeAcceleratorTypeacceleratorTypeAcceleratorTypeAcceleratorTypeAcceleratorTypeAcceleratorTypeAcceleratorType= none#The size of the Elastic Inference (EI) instance to use for the production variant.
EI instances provide on-demand GPU computing for inference.
containerStartupHealthCheckTimeoutDurationcontainer_startup_health_check_timeoutDurationcontainerStartupHealthCheckTimeoutDurationContainerStartupHealthCheckTimeoutDurationContainerStartupHealthCheckTimeoutDuration= none#The timeout value, in seconds, for your inference container to pass health check.
Range between 60 and 3600 seconds.
initialInstanceCountnumberinitial_instance_countint | floatinitialInstanceCountNumberInitialInstanceCountdoubleInitialInstanceCount*float64= 1#Number of instances to launch initially.
initialVariantWeightnumberinitial_variant_weightint | floatinitialVariantWeightNumberInitialVariantWeightdoubleInitialVariantWeight*float64= 1.0#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.
instanceTypeInstanceTypeinstance_typeInstanceTypeinstanceTypeInstanceTypeInstanceTypeInstanceTypeInstanceTypeInstanceType= InstanceType.T2_MEDIUM#Instance type of the production variant.
Name of the production variant.