Class CfnEndpointConfig.ProductionVariantProperty.Jsii$Proxy
- All Implemented Interfaces:
CfnEndpointConfig.ProductionVariantProperty,software.amazon.jsii.JsiiSerializable
- Enclosing interface:
CfnEndpointConfig.ProductionVariantProperty
CfnEndpointConfig.ProductionVariantProperty-
Nested Class Summary
Nested classes/interfaces inherited from class software.amazon.jsii.JsiiObject
software.amazon.jsii.JsiiObject.InitializationModeNested classes/interfaces inherited from interface software.amazon.awscdk.services.sagemaker.CfnEndpointConfig.ProductionVariantProperty
CfnEndpointConfig.ProductionVariantProperty.Builder, CfnEndpointConfig.ProductionVariantProperty.Jsii$Proxy -
Constructor Summary
ConstructorsModifierConstructorDescriptionprotectedConstructor that initializes the object based on literal property values passed by theCfnEndpointConfig.ProductionVariantProperty.Builder.protectedJsii$Proxy(software.amazon.jsii.JsiiObjectRef objRef) Constructor that initializes the object based on values retrieved from the JsiiObject. -
Method Summary
Modifier and TypeMethodDescriptioncom.fasterxml.jackson.databind.JsonNodefinal booleanfinal StringThe size of the Elastic Inference (EI) instance to use for the production variant.final ObjectSettings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.final NumberThe timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.final ObjectSpecifies where SageMaker writes core dumps from the model container when the process crashes, and how it encrypts them.final ObjectYou can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint.final StringSpecifies an option from a collection of preconfigured Amazon Machine Image (AMI) images.final NumberNumber of instances to launch initially.final NumberDetermines initial traffic distribution among all of the models that you specify in the endpoint configuration.final ObjectA list of instance pools for the production variant.final StringThe ML compute instance type.final ObjectSettings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.final NumberThe 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.final StringThe name of the model that you want to host.final ObjectSettings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.final ObjectThe serverless configuration for an endpoint.final NumberThe timeout value, in seconds, for provisioning instances for the production variant.final StringThe name of the production variant.final NumberThe size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant.final inthashCode()Methods inherited from class software.amazon.jsii.JsiiObject
jsiiAsyncCall, jsiiAsyncCall, jsiiCall, jsiiCall, jsiiGet, jsiiGet, jsiiSet, jsiiStaticCall, jsiiStaticCall, jsiiStaticGet, jsiiStaticGet, jsiiStaticSet, jsiiStaticSet
-
Constructor Details
-
Jsii$Proxy
protected Jsii$Proxy(software.amazon.jsii.JsiiObjectRef objRef) Constructor that initializes the object based on values retrieved from the JsiiObject.- Parameters:
objRef- Reference to the JSII managed object.
-
Jsii$Proxy
Constructor that initializes the object based on literal property values passed by theCfnEndpointConfig.ProductionVariantProperty.Builder.
-
-
Method Details
-
getVariantName
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe name of the production variant.- Specified by:
getVariantNamein interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getAcceleratorType
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe 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 .
- Specified by:
getAcceleratorTypein interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getCapacityReservationConfig
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertySettings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.Returns union: either
IResolvableorCfnEndpointConfig.CapacityReservationConfigProperty- Specified by:
getCapacityReservationConfigin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getContainerStartupHealthCheckTimeoutInSeconds
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe 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 .
- Specified by:
getContainerStartupHealthCheckTimeoutInSecondsin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getCoreDumpConfig
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertySpecifies where SageMaker writes core dumps from the model container when the process crashes, and how it encrypts them.Returns union: either
IResolvableorCfnEndpointConfig.CoreDumpConfigProperty- Specified by:
getCoreDumpConfigin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getEnableSsmAccess
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyYou 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 union: either
BooleanorIResolvable- Specified by:
getEnableSsmAccessin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getInferenceAmiVersion
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertySpecifies 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
- Specified by:
getInferenceAmiVersionin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getInitialInstanceCount
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyNumber of instances to launch initially.- Specified by:
getInitialInstanceCountin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getInitialVariantWeight
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyDetermines 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
VariantWeightto the sum of allVariantWeightvalues across all ProductionVariants. If unspecified, it defaults to 1.0.- Specified by:
getInitialVariantWeightin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getInstancePools
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyA 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 union: either
IResolvableor Listinvalid input: '<'eitherIResolvableorCfnEndpointConfig.InstancePoolProperty>- Specified by:
getInstancePoolsin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getInstanceType
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe ML compute instance type.- Specified by:
getInstanceTypein interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getManagedInstanceScaling
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertySettings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.Returns union: either
IResolvableorCfnEndpointConfig.ManagedInstanceScalingProperty- Specified by:
getManagedInstanceScalingin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getModelDataDownloadTimeoutInSeconds
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe 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.- Specified by:
getModelDataDownloadTimeoutInSecondsin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getModelName
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe name of the model that you want to host.This is the name that you specified when creating the model.
- Specified by:
getModelNamein interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getRoutingConfig
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertySettings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.Returns union: either
IResolvableorCfnEndpointConfig.RoutingConfigProperty- Specified by:
getRoutingConfigin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getServerlessConfig
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe serverless configuration for an endpoint.Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
Returns union: either
IResolvableorCfnEndpointConfig.ServerlessConfigProperty- Specified by:
getServerlessConfigin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getVariantInstanceProvisionTimeoutInSeconds
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe 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.
- Specified by:
getVariantInstanceProvisionTimeoutInSecondsin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
getVolumeSizeInGb
Description copied from interface:CfnEndpointConfig.ProductionVariantPropertyThe 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.
- Specified by:
getVolumeSizeInGbin interfaceCfnEndpointConfig.ProductionVariantProperty- See Also:
-
$jsii$toJson
@Internal public com.fasterxml.jackson.databind.JsonNode $jsii$toJson()- Specified by:
$jsii$toJsonin interfacesoftware.amazon.jsii.JsiiSerializable
-
equals
-
hashCode
public final int hashCode()
-