Package software.amazon.awscdk.services.sagemaker

Class CfnEndpointConfig.ProductionVariantProperty.Builder

java.lang.Object

software.amazon.awscdk.services.sagemaker.CfnEndpointConfig.ProductionVariantProperty.Builder

All Implemented Interfaces:

software.amazon.jsii.Builder<CfnEndpointConfig.ProductionVariantProperty>

Enclosing interface:

CfnEndpointConfig.ProductionVariantProperty

@Stability(Stable)
public static final class CfnEndpointConfig.ProductionVariantProperty.Builder
extends Object
implements software.amazon.jsii.Builder<CfnEndpointConfig.ProductionVariantProperty>

A builder for CfnEndpointConfig.ProductionVariantProperty

Constructor Summary

Constructors

Constructor	Description
Builder()

Method Summary

Modifier and Type	Method	Description
CfnEndpointConfig.ProductionVariantProperty.Builder	acceleratorType(String acceleratorType)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getAcceleratorType()
CfnEndpointConfig.ProductionVariantProperty	build()	Builds the configured instance.
CfnEndpointConfig.ProductionVariantProperty.Builder	capacityReservationConfig(IResolvable capacityReservationConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCapacityReservationConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	capacityReservationConfig(CfnEndpointConfig.CapacityReservationConfigProperty capacityReservationConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCapacityReservationConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	containerStartupHealthCheckTimeoutInSeconds(Number containerStartupHealthCheckTimeoutInSeconds)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getContainerStartupHealthCheckTimeoutInSeconds()
CfnEndpointConfig.ProductionVariantProperty.Builder	coreDumpConfig(IResolvable coreDumpConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCoreDumpConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	coreDumpConfig(CfnEndpointConfig.CoreDumpConfigProperty coreDumpConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCoreDumpConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	enableSsmAccess(Boolean enableSsmAccess)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getEnableSsmAccess()
CfnEndpointConfig.ProductionVariantProperty.Builder	enableSsmAccess(IResolvable enableSsmAccess)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getEnableSsmAccess()
CfnEndpointConfig.ProductionVariantProperty.Builder	inferenceAmiVersion(String inferenceAmiVersion)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInferenceAmiVersion()
CfnEndpointConfig.ProductionVariantProperty.Builder	initialInstanceCount(Number initialInstanceCount)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInitialInstanceCount()
CfnEndpointConfig.ProductionVariantProperty.Builder	initialVariantWeight(Number initialVariantWeight)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInitialVariantWeight()
CfnEndpointConfig.ProductionVariantProperty.Builder	instancePools(List<? extends Object> instancePools)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInstancePools()
CfnEndpointConfig.ProductionVariantProperty.Builder	instancePools(IResolvable instancePools)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInstancePools()
CfnEndpointConfig.ProductionVariantProperty.Builder	instanceType(String instanceType)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInstanceType()
CfnEndpointConfig.ProductionVariantProperty.Builder	managedInstanceScaling(IResolvable managedInstanceScaling)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getManagedInstanceScaling()
CfnEndpointConfig.ProductionVariantProperty.Builder	managedInstanceScaling(CfnEndpointConfig.ManagedInstanceScalingProperty managedInstanceScaling)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getManagedInstanceScaling()
CfnEndpointConfig.ProductionVariantProperty.Builder	modelDataDownloadTimeoutInSeconds(Number modelDataDownloadTimeoutInSeconds)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getModelDataDownloadTimeoutInSeconds()
CfnEndpointConfig.ProductionVariantProperty.Builder	modelName(String modelName)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getModelName()
CfnEndpointConfig.ProductionVariantProperty.Builder	routingConfig(IResolvable routingConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getRoutingConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	routingConfig(CfnEndpointConfig.RoutingConfigProperty routingConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getRoutingConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	serverlessConfig(IResolvable serverlessConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getServerlessConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	serverlessConfig(CfnEndpointConfig.ServerlessConfigProperty serverlessConfig)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getServerlessConfig()
CfnEndpointConfig.ProductionVariantProperty.Builder	variantInstanceProvisionTimeoutInSeconds(Number variantInstanceProvisionTimeoutInSeconds)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getVariantInstanceProvisionTimeoutInSeconds()
CfnEndpointConfig.ProductionVariantProperty.Builder	variantName(String variantName)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getVariantName()
CfnEndpointConfig.ProductionVariantProperty.Builder	volumeSizeInGb(Number volumeSizeInGb)	Sets the value of CfnEndpointConfig.ProductionVariantProperty.getVolumeSizeInGb()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

Builder

public Builder()

Method Details

variantName

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder variantName(String variantName)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getVariantName()

Parameters:

variantName - The name of the production variant. This parameter is required.

Returns:

this

acceleratorType

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder acceleratorType(String acceleratorType)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getAcceleratorType()

Parameters:

acceleratorType - The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker . For more information, see Using Elastic Inference in Amazon SageMaker .

Returns:

this

capacityReservationConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder capacityReservationConfig(IResolvable capacityReservationConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCapacityReservationConfig()

Parameters:

capacityReservationConfig - Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.

Returns:

this

capacityReservationConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder capacityReservationConfig(CfnEndpointConfig.CapacityReservationConfigProperty capacityReservationConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCapacityReservationConfig()

Parameters:

capacityReservationConfig - Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.

Returns:

this

containerStartupHealthCheckTimeoutInSeconds

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder containerStartupHealthCheckTimeoutInSeconds(Number containerStartupHealthCheckTimeoutInSeconds)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getContainerStartupHealthCheckTimeoutInSeconds()

Parameters:

containerStartupHealthCheckTimeoutInSeconds - The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests .

Returns:

this

coreDumpConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder coreDumpConfig(IResolvable coreDumpConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCoreDumpConfig()

Parameters:

coreDumpConfig - Specifies where SageMaker writes core dumps from the model container when the process crashes, and how it encrypts them.

Returns:

this

coreDumpConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder coreDumpConfig(CfnEndpointConfig.CoreDumpConfigProperty coreDumpConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getCoreDumpConfig()

Parameters:

coreDumpConfig - Specifies where SageMaker writes core dumps from the model container when the process crashes, and how it encrypts them.

Returns:

this

enableSsmAccess

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder enableSsmAccess(Boolean enableSsmAccess)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getEnableSsmAccess()

Parameters:

enableSsmAccess - You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint. You can turn on or turn off SSM access for a production variant behind an existing endpoint by creating a new endpoint configuration and calling UpdateEndpoint .

Returns:

this

enableSsmAccess

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder enableSsmAccess(IResolvable enableSsmAccess)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getEnableSsmAccess()

Parameters:

enableSsmAccess - You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint. You can turn on or turn off SSM access for a production variant behind an existing endpoint by creating a new endpoint configuration and calling UpdateEndpoint .

Returns:

this

inferenceAmiVersion

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder inferenceAmiVersion(String inferenceAmiVersion)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInferenceAmiVersion()

Parameters:

inferenceAmiVersion - Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions

Returns:

this

initialInstanceCount

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder initialInstanceCount(Number initialInstanceCount)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInitialInstanceCount()

Parameters:

initialInstanceCount - Number of instances to launch initially.

Returns:

this

initialVariantWeight

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder initialVariantWeight(Number initialVariantWeight)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInitialVariantWeight()

Parameters:

initialVariantWeight - 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 VariantWeight to the sum of all VariantWeight values across all ProductionVariants. If unspecified, it defaults to 1.0.

Returns:

this

instancePools

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder instancePools(IResolvable instancePools)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInstancePools()

Parameters:

instancePools - A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.

Returns:

this

instancePools

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder instancePools(List<? extends Object> instancePools)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInstancePools()

Parameters:

instancePools - A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.

Returns:

this

instanceType

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder instanceType(String instanceType)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getInstanceType()

Parameters:

instanceType - The ML compute instance type.

Returns:

this

managedInstanceScaling

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder managedInstanceScaling(IResolvable managedInstanceScaling)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getManagedInstanceScaling()

Parameters:

managedInstanceScaling - Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.

Returns:

this

managedInstanceScaling

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder managedInstanceScaling(CfnEndpointConfig.ManagedInstanceScalingProperty managedInstanceScaling)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getManagedInstanceScaling()

Parameters:

managedInstanceScaling - Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.

Returns:

this

modelDataDownloadTimeoutInSeconds

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder modelDataDownloadTimeoutInSeconds(Number modelDataDownloadTimeoutInSeconds)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getModelDataDownloadTimeoutInSeconds()

Parameters:

modelDataDownloadTimeoutInSeconds - The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.

Returns:

this

modelName

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder modelName(String modelName)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getModelName()

Parameters:

modelName - The name of the model that you want to host. This is the name that you specified when creating the model.

Returns:

this

routingConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder routingConfig(IResolvable routingConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getRoutingConfig()

Parameters:

routingConfig - Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.

Returns:

this

routingConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder routingConfig(CfnEndpointConfig.RoutingConfigProperty routingConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getRoutingConfig()

Parameters:

routingConfig - Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.

Returns:

this

serverlessConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder serverlessConfig(IResolvable serverlessConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getServerlessConfig()

Parameters:

serverlessConfig - The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.

Returns:

this

serverlessConfig

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder serverlessConfig(CfnEndpointConfig.ServerlessConfigProperty serverlessConfig)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getServerlessConfig()

Parameters:

serverlessConfig - The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.

Returns:

this

variantInstanceProvisionTimeoutInSeconds

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder variantInstanceProvisionTimeoutInSeconds(Number variantInstanceProvisionTimeoutInSeconds)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getVariantInstanceProvisionTimeoutInSeconds()

Parameters:

variantInstanceProvisionTimeoutInSeconds - The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.

Returns:

this

volumeSizeInGb

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty.Builder volumeSizeInGb(Number volumeSizeInGb)

Sets the value of CfnEndpointConfig.ProductionVariantProperty.getVolumeSizeInGb()

Parameters:

volumeSizeInGb - The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

Returns:

this

build

@Stability(Stable)
public CfnEndpointConfig.ProductionVariantProperty build()

Builds the configured instance.

Specified by:

build in interface software.amazon.jsii.Builder<CfnEndpointConfig.ProductionVariantProperty>

Returns:

a new instance of CfnEndpointConfig.ProductionVariantProperty

Throws:

NullPointerException - if any required attribute was not provided