Interface IInvocationsScalingProps

(experimental) Properties for enabling SageMaker Endpoint utilization tracking.

Inherited Members
Namespace: Amazon.CDK.AWS.Sagemaker.Alpha
Assembly: Amazon.CDK.AWS.Sagemaker.Alpha.dll
Syntax (csharp)
public interface IInvocationsScalingProps : IBaseTargetTrackingProps
Syntax (vb)
Public Interface IInvocationsScalingProps Inherits IBaseTargetTrackingProps
Remarks

Stability: Experimental

ExampleMetadata: infused

Examples
using Amazon.CDK.AWS.Sagemaker.Alpha;

             Model model;


             var variantName = "my-variant";
             var endpointConfig = new EndpointConfig(this, "EndpointConfig", new EndpointConfigProps {
                 InstanceProductionVariants = new [] { new InstanceProductionVariantProps {
                     Model = model,
                     VariantName = variantName
                 } }
             });

             var endpoint = new Endpoint(this, "Endpoint", new EndpointProps { EndpointConfig = endpointConfig });
             var productionVariant = endpoint.FindInstanceProductionVariant(variantName);
             var instanceCount = productionVariant.AutoScaleInstanceCount(new EnableScalingProps {
                 MaxCapacity = 3
             });
             instanceCount.ScaleOnInvocations("LimitRPS", new InvocationsScalingProps {
                 MaxRequestsPerSecond = 30
             });

Synopsis

Properties

MaxRequestsPerSecond

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

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

Properties

MaxRequestsPerSecond

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

double MaxRequestsPerSecond { get; }
Property Value

double

Remarks

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

Stability: Experimental

SafetyFactor

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

double? SafetyFactor { get; }
Property Value

double?

Remarks

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

Default: 0.5

Stability: Experimental