public static interface CfnEndpointConfig.ProductionVariantProperty
If you are deploying multiple models, tell Amazon SageMaker how to distribute traffic among the models by specifying the InitialVariantWeight
objects.
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.sagemaker.*; ProductionVariantProperty productionVariantProperty = ProductionVariantProperty.builder() .initialVariantWeight(123) .modelName("modelName") .variantName("variantName") // the properties below are optional .acceleratorType("acceleratorType") .containerStartupHealthCheckTimeoutInSeconds(123) .initialInstanceCount(123) .instanceType("instanceType") .modelDataDownloadTimeoutInSeconds(123) .serverlessConfig(ServerlessConfigProperty.builder() .maxConcurrency(123) .memorySizeInMb(123) .build()) .volumeSizeInGb(123) .build();
Modifier and Type | Interface and Description |
---|---|
static class |
CfnEndpointConfig.ProductionVariantProperty.Builder
A builder for
CfnEndpointConfig.ProductionVariantProperty |
static class |
CfnEndpointConfig.ProductionVariantProperty.Jsii$Proxy
An implementation for
CfnEndpointConfig.ProductionVariantProperty |
Modifier and Type | Method and Description |
---|---|
static CfnEndpointConfig.ProductionVariantProperty.Builder |
builder() |
default java.lang.String |
getAcceleratorType()
The size of the Elastic Inference (EI) instance to use for the production variant.
|
default java.lang.Number |
getContainerStartupHealthCheckTimeoutInSeconds()
`CfnEndpointConfig.ProductionVariantProperty.ContainerStartupHealthCheckTimeoutInSeconds`.
|
default java.lang.Number |
getInitialInstanceCount()
Number of instances to launch initially.
|
java.lang.Number |
getInitialVariantWeight()
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
|
default java.lang.String |
getInstanceType()
The ML compute instance type.
|
default java.lang.Number |
getModelDataDownloadTimeoutInSeconds()
`CfnEndpointConfig.ProductionVariantProperty.ModelDataDownloadTimeoutInSeconds`.
|
java.lang.String |
getModelName()
The name of the model that you want to host.
|
default java.lang.Object |
getServerlessConfig()
The serverless configuration for an endpoint.
|
java.lang.String |
getVariantName()
The name of the production variant.
|
default java.lang.Number |
getVolumeSizeInGb()
`CfnEndpointConfig.ProductionVariantProperty.VolumeSizeInGB`.
|
java.lang.Number getInitialVariantWeight()
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.
java.lang.String getModelName()
This is the name that you specified when creating the model.
java.lang.String getVariantName()
default java.lang.String getAcceleratorType()
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 .
default java.lang.Number getContainerStartupHealthCheckTimeoutInSeconds()
default java.lang.Number getInitialInstanceCount()
default java.lang.String getInstanceType()
default java.lang.Number getModelDataDownloadTimeoutInSeconds()
default java.lang.Object getServerlessConfig()
Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
default java.lang.Number getVolumeSizeInGb()
static CfnEndpointConfig.ProductionVariantProperty.Builder builder()