Package software.amazon.awscdk.services.sagemaker.alpha

Interface ServerlessProductionVariantProps

All Superinterfaces:

software.amazon.jsii.JsiiSerializable

All Known Implementing Classes:

ServerlessProductionVariantProps.Jsii$Proxy

@Generated(value="jsii-pacmak/1.119.0 (build 1634eac)",
           date="2025-11-17T14:41:05.250Z")
@Stability(Experimental)
public interface ServerlessProductionVariantProps
extends software.amazon.jsii.JsiiSerializable

(experimental) Construction properties for a serverless production variant.

Example:

 import software.amazon.awscdk.services.sagemaker.alpha.*;
 Model model;
 EndpointConfig endpointConfig = EndpointConfig.Builder.create(this, "ServerlessEndpointConfig")
         .serverlessProductionVariant(ServerlessProductionVariantProps.builder()
                 .model(model)
                 .variantName("serverlessVariant")
                 .maxConcurrency(10)
                 .memorySizeInMB(2048)
                 .provisionedConcurrency(5)
                 .build())
         .build();
 

Nested Class Summary

Nested Classes

Modifier and Type	Interface	Description
static final class	ServerlessProductionVariantProps.Builder	A builder for ServerlessProductionVariantProps
static final class	ServerlessProductionVariantProps.Jsii$Proxy	An implementation for ServerlessProductionVariantProps

Method Summary

Modifier and Type	Method	Description
static ServerlessProductionVariantProps.Builder	builder()
default Number	getInitialVariantWeight()	(experimental) Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
Number	getMaxConcurrency()	(experimental) The maximum number of concurrent invocations your serverless endpoint can process.
Number	getMemorySizeInMB()	(experimental) The memory size of your serverless endpoint.
IModel	getModel()	(experimental) The model to host.
default Number	getProvisionedConcurrency()	(experimental) The number of concurrent invocations that are provisioned and ready to respond to your endpoint.
String	getVariantName()	(experimental) Name of the production variant.

Methods inherited from interface software.amazon.jsii.JsiiSerializable

$jsii$toJson

Method Details

getMaxConcurrency

@Stability(Experimental)
@NotNull
Number getMaxConcurrency()

(experimental) The maximum number of concurrent invocations your serverless endpoint can process.

Valid range: 1-200

getMemorySizeInMB

@Stability(Experimental)
@NotNull
Number getMemorySizeInMB()

(experimental) The memory size of your serverless endpoint.

Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.

getModel

@Stability(Experimental)
@NotNull
IModel getModel()

(experimental) The model to host.

getVariantName

@Stability(Experimental)
@NotNull
String getVariantName()

(experimental) Name of the production variant.

getInitialVariantWeight

@Stability(Experimental)
@Nullable
default Number getInitialVariantWeight()

(experimental) 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.

Default: 1.0

getProvisionedConcurrency

@Stability(Experimental)
@Nullable
default Number getProvisionedConcurrency()

(experimental) The number of concurrent invocations that are provisioned and ready to respond to your endpoint.

Valid range: 1-200, must be less than or equal to maxConcurrency.

Default: - none

builder

@Stability(Experimental)
static ServerlessProductionVariantProps.Builder builder()

Returns:

a ServerlessProductionVariantProps.Builder of ServerlessProductionVariantProps