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

Interface InvocationsScalingProps

All Superinterfaces:

BaseTargetTrackingProps, software.amazon.jsii.JsiiSerializable

All Known Implementing Classes:

InvocationsScalingProps.Jsii$Proxy

@Generated(value="jsii-pacmak/1.104.0 (build e79254c)",
           date="2024-11-22T02:24:11.856Z")
@Stability(Experimental)
public interface InvocationsScalingProps
extends software.amazon.jsii.JsiiSerializable, BaseTargetTrackingProps

(experimental) Properties for enabling SageMaker Endpoint utilization tracking.

Example:

 import software.amazon.awscdk.services.sagemaker.alpha.*;
 Model model;
 String variantName = "my-variant";
 EndpointConfig endpointConfig = EndpointConfig.Builder.create(this, "EndpointConfig")
         .instanceProductionVariants(List.of(InstanceProductionVariantProps.builder()
                 .model(model)
                 .variantName(variantName)
                 .build()))
         .build();
 Endpoint endpoint = Endpoint.Builder.create(this, "Endpoint").endpointConfig(endpointConfig).build();
 IEndpointInstanceProductionVariant productionVariant = endpoint.findInstanceProductionVariant(variantName);
 ScalableInstanceCount instanceCount = productionVariant.autoScaleInstanceCount(EnableScalingProps.builder()
         .maxCapacity(3)
         .build());
 instanceCount.scaleOnInvocations("LimitRPS", InvocationsScalingProps.builder()
         .maxRequestsPerSecond(30)
         .build());
 

Nested Class Summary

Nested Classes

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

Method Summary

Modifier and Type	Method	Description
static InvocationsScalingProps.Builder	builder()
Number	getMaxRequestsPerSecond()	(experimental) Max RPS per instance used for calculating the target SageMaker variant invocation per instance.
default Number	getSafetyFactor()	(experimental) Safty factor for calculating the target SageMaker variant invocation per instance.

Methods inherited from interface software.amazon.awscdk.services.applicationautoscaling.BaseTargetTrackingProps

getDisableScaleIn, getPolicyName, getScaleInCooldown, getScaleOutCooldown

Methods inherited from interface software.amazon.jsii.JsiiSerializable

$jsii$toJson

Method Details

getMaxRequestsPerSecond

@Stability(Experimental)
@NotNull
Number getMaxRequestsPerSecond()

(experimental) Max RPS per instance used for calculating the target SageMaker variant invocation per instance.

More documentation available here: https://docs.aws.amazon.com/sagemaker/latest/dg/endpoint-scaling-loadtest.html

getSafetyFactor

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

(experimental) Safty factor for calculating the target SageMaker variant invocation per instance.

More documentation available here: https://docs.aws.amazon.com/sagemaker/latest/dg/endpoint-scaling-loadtest.html

Default: 0.5

builder

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

Returns:

a InvocationsScalingProps.Builder of InvocationsScalingProps