Show / Hide Table of Contents

Class ScalableInstanceCount

(experimental) A scalable sagemaker endpoint attribute.

Inheritance
object
BaseScalableAttribute
ScalableInstanceCount
Inherited Members
BaseScalableAttribute.DoScaleOnMetric(string, IBasicStepScalingPolicyProps)
BaseScalableAttribute.DoScaleOnSchedule(string, IScalingSchedule)
BaseScalableAttribute.DoScaleToTrackMetric(string, IBasicTargetTrackingScalingPolicyProps)
BaseScalableAttribute.Props
Namespace: Amazon.CDK.AWS.Sagemaker.Alpha
Assembly: Amazon.CDK.AWS.Sagemaker.Alpha.dll
Syntax (csharp)
public class ScalableInstanceCount : BaseScalableAttribute
Syntax (vb)
Public Class ScalableInstanceCount Inherits BaseScalableAttribute
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

Constructors

ScalableInstanceCount(Construct, string, IScalableInstanceCountProps)

(experimental) Constructs a new instance of the ScalableInstanceCount class.

Methods

ScaleOnInvocations(string, IInvocationsScalingProps)

(experimental) Scales in or out to achieve a target requests per second per instance.

Constructors

ScalableInstanceCount(Construct, string, IScalableInstanceCountProps)

(experimental) Constructs a new instance of the ScalableInstanceCount class.

public ScalableInstanceCount(Construct scope, string id, IScalableInstanceCountProps props)
Parameters
scope Construct
id string
props IScalableInstanceCountProps
Remarks

Stability: Experimental

Methods

ScaleOnInvocations(string, IInvocationsScalingProps)

(experimental) Scales in or out to achieve a target requests per second per instance.

public virtual void ScaleOnInvocations(string id, IInvocationsScalingProps props)
Parameters
id string
props IInvocationsScalingProps
Remarks

Stability: Experimental

Back to top Generated by DocFX