Class CfnInferenceComponent

Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.

Inheritance

object

CfnElement

CfnRefElement

CfnResource

CfnInferenceComponent

Implements

IInspectable

ITaggableV2

Inherited Members

CfnResource.IsCfnResource(object)

CfnResource.AddDeletionOverride(string)

CfnResource.AddDependency(CfnResource)

CfnResource.AddDependsOn(CfnResource)

CfnResource.AddMetadata(string, object)

CfnResource.AddOverride(string, object)

CfnResource.AddPropertyDeletionOverride(string)

CfnResource.AddPropertyOverride(string, object)

CfnResource.ApplyRemovalPolicy(RemovalPolicy?, IRemovalPolicyOptions)

CfnResource.GetAtt(string, ResolutionTypeHint?)

CfnResource.GetMetadata(string)

CfnResource.ObtainDependencies()

CfnResource.ObtainResourceDependencies()

CfnResource.RemoveDependency(CfnResource)

CfnResource.ReplaceDependency(CfnResource, CfnResource)

CfnResource.ShouldSynthesize()

CfnResource.ToString()

CfnResource.ValidateProperties(object)

CfnResource.CfnOptions

CfnResource.CfnResourceType

CfnResource.UpdatedProperites

CfnResource.UpdatedProperties

CfnRefElement.Ref

CfnElement.IsCfnElement(object)

CfnElement.OverrideLogicalId(string)

CfnElement.CreationStack

CfnElement.LogicalId

CfnElement.Stack

Namespace: Amazon.CDK.AWS.Sagemaker

Assembly: Amazon.CDK.Lib.dll

Syntax (csharp)

public class CfnInferenceComponent : CfnResource, IInspectable, ITaggableV2

Syntax (vb)

Public Class CfnInferenceComponent Inherits CfnResource Implements IInspectable, ITaggableV2

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

Examples

// The code below shows an example of how to instantiate this type.
             // The values are placeholders you should change.
             using Amazon.CDK.AWS.Sagemaker;

             var cfnInferenceComponent = new CfnInferenceComponent(this, "MyCfnInferenceComponent", new CfnInferenceComponentProps {
                 EndpointName = "endpointName",
                 Specification = new InferenceComponentSpecificationProperty {
                     BaseInferenceComponentName = "baseInferenceComponentName",
                     ComputeResourceRequirements = new InferenceComponentComputeResourceRequirementsProperty {
                         MaxMemoryRequiredInMb = 123,
                         MinMemoryRequiredInMb = 123,
                         NumberOfAcceleratorDevicesRequired = 123,
                         NumberOfCpuCoresRequired = 123
                     },
                     Container = new InferenceComponentContainerSpecificationProperty {
                         ArtifactUrl = "artifactUrl",
                         DeployedImage = new DeployedImageProperty {
                             ResolutionTime = "resolutionTime",
                             ResolvedImage = "resolvedImage",
                             SpecifiedImage = "specifiedImage"
                         },
                         Environment = new Dictionary<string, string> {
                             { "environmentKey", "environment" }
                         },
                         Image = "image"
                     },
                     ModelName = "modelName",
                     StartupParameters = new InferenceComponentStartupParametersProperty {
                         ContainerStartupHealthCheckTimeoutInSeconds = 123,
                         ModelDataDownloadTimeoutInSeconds = 123
                     }
                 },

                 // the properties below are optional
                 DeploymentConfig = new InferenceComponentDeploymentConfigProperty {
                     AutoRollbackConfiguration = new AutoRollbackConfigurationProperty {
                         Alarms = new [] { new AlarmProperty {
                             AlarmName = "alarmName"
                         } }
                     },
                     RollingUpdatePolicy = new InferenceComponentRollingUpdatePolicyProperty {
                         MaximumBatchSize = new InferenceComponentCapacitySizeProperty {
                             Type = "type",
                             Value = 123
                         },
                         MaximumExecutionTimeoutInSeconds = 123,
                         RollbackMaximumBatchSize = new InferenceComponentCapacitySizeProperty {
                             Type = "type",
                             Value = 123
                         },
                         WaitIntervalInSeconds = 123
                     }
                 },
                 EndpointArn = "endpointArn",
                 InferenceComponentName = "inferenceComponentName",
                 RuntimeConfig = new InferenceComponentRuntimeConfigProperty {
                     CopyCount = 123,
                     CurrentCopyCount = 123,
                     DesiredCopyCount = 123
                 },
                 Tags = new [] { new CfnTag {
                     Key = "key",
                     Value = "value"
                 } },
                 VariantName = "variantName"
             });

Synopsis

Constructors

CfnInferenceComponent(Construct, string, ICfnInferenceComponentProps)

Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.

Properties

AttrCreationTime	The time when the inference component was created.
AttrFailureReason	The failure reason if the inference component is in a failed state.
AttrInferenceComponentArn	The Amazon Resource Name (ARN) of the inference component.
AttrInferenceComponentStatus	The status of the inference component.
AttrLastModifiedTime	The time when the inference component was last updated.
AttrRuntimeConfigCurrentCopyCount	The number of runtime copies of the model container that are currently deployed.
AttrRuntimeConfigDesiredCopyCount	The number of runtime copies of the model container that you requested to deploy with the inference component.
AttrSpecificationContainerDeployedImage	Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.
CFN_RESOURCE_TYPE_NAME	The CloudFormation resource type name for this resource class.
CdkTagManager	Tag Manager which manages the tags for this resource.
CfnProperties	Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.
DeploymentConfig	The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations.
EndpointArn	The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
EndpointName	The name of the endpoint that hosts the inference component.
InferenceComponentName	The name of the inference component.
RuntimeConfig	The runtime config for the inference component.
Specification	The specification for the inference component.
Tags	An array of tags to apply to the resource.
VariantName	The name of the production variant that hosts the inference component.

Methods

Inspect(TreeInspector)	Examines the CloudFormation resource and discloses attributes.
RenderProperties(IDictionary<string, object>)	Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.

Constructors

CfnInferenceComponent(Construct, string, ICfnInferenceComponentProps)

Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.

public CfnInferenceComponent(Construct scope, string id, ICfnInferenceComponentProps props)

Parameters

scope Construct

Scope in which this resource is defined.

id string

Construct identifier for this resource (unique in its scope).

props ICfnInferenceComponentProps

Resource properties.

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

Properties

AttrCreationTime

The time when the inference component was created.

public virtual string AttrCreationTime { get; }

Property Value

string

Remarks

CloudformationAttribute: CreationTime

AttrFailureReason

The failure reason if the inference component is in a failed state.

public virtual string AttrFailureReason { get; }

Property Value

string

Remarks

CloudformationAttribute: FailureReason

AttrInferenceComponentArn

The Amazon Resource Name (ARN) of the inference component.

public virtual string AttrInferenceComponentArn { get; }

Property Value

string

Remarks

CloudformationAttribute: InferenceComponentArn

AttrInferenceComponentStatus

The status of the inference component.

public virtual string AttrInferenceComponentStatus { get; }

Property Value

string

Remarks

CloudformationAttribute: InferenceComponentStatus

AttrLastModifiedTime

The time when the inference component was last updated.

public virtual string AttrLastModifiedTime { get; }

Property Value

string

Remarks

CloudformationAttribute: LastModifiedTime

AttrRuntimeConfigCurrentCopyCount

The number of runtime copies of the model container that are currently deployed.

public virtual double AttrRuntimeConfigCurrentCopyCount { get; }

Property Value

double

Remarks

CloudformationAttribute: RuntimeConfig.CurrentCopyCount

AttrRuntimeConfigDesiredCopyCount

The number of runtime copies of the model container that you requested to deploy with the inference component.

public virtual double AttrRuntimeConfigDesiredCopyCount { get; }

Property Value

double

Remarks

CloudformationAttribute: RuntimeConfig.DesiredCopyCount

AttrSpecificationContainerDeployedImage

Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.

public virtual IResolvable AttrSpecificationContainerDeployedImage { get; }

Property Value

IResolvable

Remarks

CloudformationAttribute: Specification.Container.DeployedImage

CFN_RESOURCE_TYPE_NAME

The CloudFormation resource type name for this resource class.

public static string CFN_RESOURCE_TYPE_NAME { get; }

Property Value

string

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

CdkTagManager

Tag Manager which manages the tags for this resource.

public virtual TagManager CdkTagManager { get; }

Property Value

TagManager

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

CfnProperties

Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.

protected override IDictionary<string, object> CfnProperties { get; }

Property Value

IDictionary<string, object>

Overrides

CfnResource.CfnProperties

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

DeploymentConfig

The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations.

public virtual object? DeploymentConfig { get; set; }

Property Value

object

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

EndpointArn

The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.

public virtual string? EndpointArn { get; set; }

Property Value

string

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

EndpointName

The name of the endpoint that hosts the inference component.

public virtual string EndpointName { get; set; }

Property Value

string

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

InferenceComponentName

The name of the inference component.

public virtual string? InferenceComponentName { get; set; }

Property Value

string

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

RuntimeConfig

The runtime config for the inference component.

public virtual object? RuntimeConfig { get; set; }

Property Value

object

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

Specification

The specification for the inference component.

public virtual object Specification { get; set; }

Property Value

object

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

Tags

An array of tags to apply to the resource.

public virtual ICfnTag[]? Tags { get; set; }

Property Value

ICfnTag[]

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

VariantName

The name of the production variant that hosts the inference component.

public virtual string? VariantName { get; set; }

Property Value

string

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

Methods

Inspect(TreeInspector)

Examines the CloudFormation resource and discloses attributes.

public virtual void Inspect(TreeInspector inspector)

Parameters

inspector TreeInspector

tree inspector to collect and process attributes.

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

RenderProperties(IDictionary<string, object>)

Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.

protected override IDictionary<string, object> RenderProperties(IDictionary<string, object> props)

Parameters

props IDictionary<string, object>

Returns

IDictionary<string, object>

Overrides

CfnResource.RenderProperties(IDictionary<string, object>)

Remarks

In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.

See: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-inferencecomponent.html

CloudformationResource: AWS::SageMaker::InferenceComponent

ExampleMetadata: fixture=_generated

Implements

IInspectable

ITaggableV2