

This is the new *CloudFormation Template Reference Guide*. Please update your bookmarks and links. For help getting started with CloudFormation, see the [AWS CloudFormation User Guide](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/Welcome.html).

# AWS::SageMaker::InferenceComponent
<a name="aws-resource-sagemaker-inferencecomponent"></a>

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

## Syntax
<a name="aws-resource-sagemaker-inferencecomponent-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-resource-sagemaker-inferencecomponent-syntax.json"></a>

```
{
  "Type" : "AWS::SageMaker::InferenceComponent",
  "Properties" : {
      "[DeploymentConfig](#cfn-sagemaker-inferencecomponent-deploymentconfig)" : InferenceComponentDeploymentConfig,
      "[EndpointArn](#cfn-sagemaker-inferencecomponent-endpointarn)" : String,
      "[EndpointName](#cfn-sagemaker-inferencecomponent-endpointname)" : String,
      "[InferenceComponentName](#cfn-sagemaker-inferencecomponent-inferencecomponentname)" : String,
      "[RuntimeConfig](#cfn-sagemaker-inferencecomponent-runtimeconfig)" : InferenceComponentRuntimeConfig,
      "[Specification](#cfn-sagemaker-inferencecomponent-specification)" : InferenceComponentSpecification,
      "[Tags](#cfn-sagemaker-inferencecomponent-tags)" : [ Tag, ... ],
      "[VariantName](#cfn-sagemaker-inferencecomponent-variantname)" : String
    }
}
```

### YAML
<a name="aws-resource-sagemaker-inferencecomponent-syntax.yaml"></a>

```
Type: AWS::SageMaker::InferenceComponent
Properties:
  [DeploymentConfig](#cfn-sagemaker-inferencecomponent-deploymentconfig): 
    InferenceComponentDeploymentConfig
  [EndpointArn](#cfn-sagemaker-inferencecomponent-endpointarn): String
  [EndpointName](#cfn-sagemaker-inferencecomponent-endpointname): String
  [InferenceComponentName](#cfn-sagemaker-inferencecomponent-inferencecomponentname): String
  [RuntimeConfig](#cfn-sagemaker-inferencecomponent-runtimeconfig): 
    InferenceComponentRuntimeConfig
  [Specification](#cfn-sagemaker-inferencecomponent-specification): 
    InferenceComponentSpecification
  [Tags](#cfn-sagemaker-inferencecomponent-tags): 
    - Tag
  [VariantName](#cfn-sagemaker-inferencecomponent-variantname): String
```

## Properties
<a name="aws-resource-sagemaker-inferencecomponent-properties"></a>

`DeploymentConfig`  <a name="cfn-sagemaker-inferencecomponent-deploymentconfig"></a>
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations.  
*Required*: No  
*Type*: [InferenceComponentDeploymentConfig](aws-properties-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`EndpointArn`  <a name="cfn-sagemaker-inferencecomponent-endpointarn"></a>
The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.  
*Required*: No  
*Type*: String  
*Minimum*: `1`  
*Maximum*: `256`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`EndpointName`  <a name="cfn-sagemaker-inferencecomponent-endpointname"></a>
The name of the endpoint that hosts the inference component.  
*Required*: Yes  
*Type*: String  
*Pattern*: `^[a-zA-Z0-9](-*[a-zA-Z0-9])*$`  
*Maximum*: `63`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`InferenceComponentName`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentname"></a>
The name of the inference component.  
*Required*: No  
*Type*: String  
*Pattern*: `^[a-zA-Z0-9](-*[a-zA-Z0-9])*$`  
*Maximum*: `63`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`RuntimeConfig`  <a name="cfn-sagemaker-inferencecomponent-runtimeconfig"></a>
Runtime settings for the inference component, including the number of copies to deploy.  
*Required*: No  
*Type*: [InferenceComponentRuntimeConfig](aws-properties-sagemaker-inferencecomponent-inferencecomponentruntimeconfig.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`Specification`  <a name="cfn-sagemaker-inferencecomponent-specification"></a>
The specification for the inference component, including the model and container configuration.  
*Required*: Yes  
*Type*: [InferenceComponentSpecification](aws-properties-sagemaker-inferencecomponent-inferencecomponentspecification.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`Tags`  <a name="cfn-sagemaker-inferencecomponent-tags"></a>
Property description not available.  
*Required*: No  
*Type*: Array of [Tag](aws-properties-sagemaker-inferencecomponent-tag.md)  
*Maximum*: `50`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`VariantName`  <a name="cfn-sagemaker-inferencecomponent-variantname"></a>
The name of the production variant that hosts the inference component.  
*Required*: No  
*Type*: String  
*Pattern*: `^[a-zA-Z0-9](-*[a-zA-Z0-9])*$`  
*Maximum*: `63`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

## Return values
<a name="aws-resource-sagemaker-inferencecomponent-return-values"></a>

### Ref
<a name="aws-resource-sagemaker-inferencecomponent-return-values-ref"></a>

 When you pass the logical ID of this resource to the intrinsic `Ref` function, `Ref` returns the Amazon Resource Name (ARN) of the inference component.

For more information about using the `Ref` function, see [https://docs.aws.amazon.com/AWSCloudFormation/latest/TemplateReference/intrinsic-function-reference-ref.html](https://docs.aws.amazon.com/AWSCloudFormation/latest/TemplateReference/intrinsic-function-reference-ref.html).

### Fn::GetAtt
<a name="aws-resource-sagemaker-inferencecomponent-return-values-fn--getatt"></a>

The `Fn::GetAtt` intrinsic function returns a value for a specified attribute of this type. The following are the available attributes and sample return values.

For more information about using the `Fn::GetAtt` intrinsic function, see [https://docs.aws.amazon.com/AWSCloudFormation/latest/TemplateReference/intrinsic-function-reference-getatt.html](https://docs.aws.amazon.com/AWSCloudFormation/latest/TemplateReference/intrinsic-function-reference-getatt.html).

#### 
<a name="aws-resource-sagemaker-inferencecomponent-return-values-fn--getatt-fn--getatt"></a>

`CreationTime`  <a name="CreationTime-fn::getatt"></a>
The time when the inference component was created.

`FailureReason`  <a name="FailureReason-fn::getatt"></a>
The reason why the inference component failed, if applicable.

`InferenceComponentArn`  <a name="InferenceComponentArn-fn::getatt"></a>
The Amazon Resource Name (ARN) of the inference component.

`InferenceComponentStatus`  <a name="InferenceComponentStatus-fn::getatt"></a>
The status of the inference component.

`LastModifiedTime`  <a name="LastModifiedTime-fn::getatt"></a>
The time when the inference component was last updated.

`RuntimeConfig.CurrentCopyCount`  <a name="RuntimeConfig.CurrentCopyCount-fn::getatt"></a>
The number of runtime copies of the model container that are currently deployed.

`RuntimeConfig.DesiredCopyCount`  <a name="RuntimeConfig.DesiredCopyCount-fn::getatt"></a>
The number of runtime copies of the model container that you requested to deploy with the inference component.

# AWS::SageMaker::InferenceComponent Alarm
<a name="aws-properties-sagemaker-inferencecomponent-alarm"></a>

An Amazon CloudWatch alarm configured to monitor metrics on an endpoint.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-alarm-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-alarm-syntax.json"></a>

```
{
  "[AlarmName](#cfn-sagemaker-inferencecomponent-alarm-alarmname)" : String
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-alarm-syntax.yaml"></a>

```
  [AlarmName](#cfn-sagemaker-inferencecomponent-alarm-alarmname): String
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-alarm-properties"></a>

`AlarmName`  <a name="cfn-sagemaker-inferencecomponent-alarm-alarmname"></a>
The name of a CloudWatch alarm in your account.  
*Required*: Yes  
*Type*: String  
*Pattern*: `^(?!\s*$).+`  
*Minimum*: `1`  
*Maximum*: `255`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent AutoRollbackConfiguration
<a name="aws-properties-sagemaker-inferencecomponent-autorollbackconfiguration"></a>

Configuration for automatic rollback of the inference component deployment if issues are detected.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-autorollbackconfiguration-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-autorollbackconfiguration-syntax.json"></a>

```
{
  "[Alarms](#cfn-sagemaker-inferencecomponent-autorollbackconfiguration-alarms)" : [ Alarm, ... ]
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-autorollbackconfiguration-syntax.yaml"></a>

```
  [Alarms](#cfn-sagemaker-inferencecomponent-autorollbackconfiguration-alarms): 
    - Alarm
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-autorollbackconfiguration-properties"></a>

`Alarms`  <a name="cfn-sagemaker-inferencecomponent-autorollbackconfiguration-alarms"></a>
List of CloudWatch alarms that trigger automatic rollback if they enter the ALARM state during deployment.  
*Required*: Yes  
*Type*: Array of [Alarm](aws-properties-sagemaker-inferencecomponent-alarm.md)  
*Minimum*: `1`  
*Maximum*: `10`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent DeployedImage
<a name="aws-properties-sagemaker-inferencecomponent-deployedimage"></a>

Gets the Amazon EC2 Container Registry path of the docker image of the model that is hosted in this [ProductionVariant](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_ProductionVariant.html).

If you used the `registry/repository[:tag]` form to specify the image path of the primary container when you created the model hosted in this `ProductionVariant`, the path resolves to a path of the form `registry/repository[@digest]`. A digest is a hash value that identifies a specific version of an image. For information about Amazon ECR paths, see [Pulling an Image](https://docs.aws.amazon.com//AmazonECR/latest/userguide/docker-pull-ecr-image.html) in the *Amazon ECR User Guide*.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-deployedimage-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-deployedimage-syntax.json"></a>

```
{
  "[ResolutionTime](#cfn-sagemaker-inferencecomponent-deployedimage-resolutiontime)" : String,
  "[ResolvedImage](#cfn-sagemaker-inferencecomponent-deployedimage-resolvedimage)" : String,
  "[SpecifiedImage](#cfn-sagemaker-inferencecomponent-deployedimage-specifiedimage)" : String
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-deployedimage-syntax.yaml"></a>

```
  [ResolutionTime](#cfn-sagemaker-inferencecomponent-deployedimage-resolutiontime): String
  [ResolvedImage](#cfn-sagemaker-inferencecomponent-deployedimage-resolvedimage): String
  [SpecifiedImage](#cfn-sagemaker-inferencecomponent-deployedimage-specifiedimage): String
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-deployedimage-properties"></a>

`ResolutionTime`  <a name="cfn-sagemaker-inferencecomponent-deployedimage-resolutiontime"></a>
The date and time when the image path for the model resolved to the `ResolvedImage`  
*Required*: No  
*Type*: String  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`ResolvedImage`  <a name="cfn-sagemaker-inferencecomponent-deployedimage-resolvedimage"></a>
The specific digest path of the image hosted in this `ProductionVariant`.  
*Required*: No  
*Type*: String  
*Pattern*: `[\S]+`  
*Maximum*: `255`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`SpecifiedImage`  <a name="cfn-sagemaker-inferencecomponent-deployedimage-specifiedimage"></a>
The image path you specified when you created the model.  
*Required*: No  
*Type*: String  
*Pattern*: `[\S]+`  
*Maximum*: `255`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentCapacitySize
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcapacitysize"></a>

Specifies the type and size of the endpoint capacity to activate for a rolling deployment or a rollback strategy. You can specify your batches as either of the following:
+ A count of inference component copies 
+ The overall percentage or your fleet 

For a rollback strategy, if you don't specify the fields in this object, or if you set the `Value` parameter to 100%, then SageMaker AI uses a blue/green rollback strategy and rolls all traffic back to the blue fleet.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcapacitysize-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcapacitysize-syntax.json"></a>

```
{
  "[Type](#cfn-sagemaker-inferencecomponent-inferencecomponentcapacitysize-type)" : String,
  "[Value](#cfn-sagemaker-inferencecomponent-inferencecomponentcapacitysize-value)" : Integer
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcapacitysize-syntax.yaml"></a>

```
  [Type](#cfn-sagemaker-inferencecomponent-inferencecomponentcapacitysize-type): String
  [Value](#cfn-sagemaker-inferencecomponent-inferencecomponentcapacitysize-value): Integer
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcapacitysize-properties"></a>

`Type`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcapacitysize-type"></a>
Specifies the endpoint capacity type.    
COPY\$1COUNT  
The endpoint activates based on the number of inference component copies.  
CAPACITY\$1PERCENT  
The endpoint activates based on the specified percentage of capacity.
*Required*: Yes  
*Type*: String  
*Allowed values*: `COPY_COUNT | CAPACITY_PERCENT`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`Value`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcapacitysize-value"></a>
Defines the capacity size, either as a number of inference component copies or a capacity percentage.  
*Required*: Yes  
*Type*: Integer  
*Minimum*: `1`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentComputeResourceRequirements
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements"></a>

Defines the compute resources to allocate to run a model, plus any adapter models, that you assign to an inference component. These resources include CPU cores, accelerators, and memory.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-syntax.json"></a>

```
{
  "[MaxMemoryRequiredInMb](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-maxmemoryrequiredinmb)" : Integer,
  "[MinMemoryRequiredInMb](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-minmemoryrequiredinmb)" : Integer,
  "[NumberOfAcceleratorDevicesRequired](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-numberofacceleratordevicesrequired)" : Number,
  "[NumberOfCpuCoresRequired](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-numberofcpucoresrequired)" : Number
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-syntax.yaml"></a>

```
  [MaxMemoryRequiredInMb](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-maxmemoryrequiredinmb): Integer
  [MinMemoryRequiredInMb](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-minmemoryrequiredinmb): Integer
  [NumberOfAcceleratorDevicesRequired](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-numberofacceleratordevicesrequired): 
    Number
  [NumberOfCpuCoresRequired](#cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-numberofcpucoresrequired): 
    Number
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-properties"></a>

`MaxMemoryRequiredInMb`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-maxmemoryrequiredinmb"></a>
The maximum MB of memory to allocate to run a model that you assign to an inference component.  
*Required*: No  
*Type*: Integer  
*Minimum*: `128`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`MinMemoryRequiredInMb`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-minmemoryrequiredinmb"></a>
The minimum MB of memory to allocate to run a model that you assign to an inference component.  
*Required*: No  
*Type*: Integer  
*Minimum*: `128`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`NumberOfAcceleratorDevicesRequired`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-numberofacceleratordevicesrequired"></a>
The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.  
*Required*: No  
*Type*: Number  
*Minimum*: `1`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`NumberOfCpuCoresRequired`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements-numberofcpucoresrequired"></a>
The number of CPU cores to allocate to run a model that you assign to an inference component.  
*Required*: No  
*Type*: Number  
*Minimum*: `0`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentContainerSpecification
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcontainerspecification"></a>

Defines a container that provides the runtime environment for a model that you deploy with an inference component.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-syntax.json"></a>

```
{
  "[ArtifactUrl](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-artifacturl)" : String,
  "[DeployedImage](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-deployedimage)" : DeployedImage,
  "[Environment](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-environment)" : {Key: Value, ...},
  "[Image](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-image)" : String
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-syntax.yaml"></a>

```
  [ArtifactUrl](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-artifacturl): String
  [DeployedImage](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-deployedimage): 
    DeployedImage
  [Environment](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-environment): 
    Key: Value
  [Image](#cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-image): String
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-properties"></a>

`ArtifactUrl`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-artifacturl"></a>
The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).  
*Required*: No  
*Type*: String  
*Pattern*: `^(https|s3)://([^/]+)/?(.*)$`  
*Maximum*: `1024`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`DeployedImage`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-deployedimage"></a>
The deployed container image for the inference component.  
*Required*: No  
*Type*: [DeployedImage](aws-properties-sagemaker-inferencecomponent-deployedimage.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`Environment`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-environment"></a>
The environment variables to set in the Docker container. Each key and value in the Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.  
*Required*: No  
*Type*: Object of String  
*Pattern*: `^[a-zA-Z_][a-zA-Z0-9_]{1,1024}$`  
*Maximum*: `1024`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`Image`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentcontainerspecification-image"></a>
The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.  
*Required*: No  
*Type*: String  
*Pattern*: `[\S]+`  
*Maximum*: `255`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentDeploymentConfig
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig"></a>

The deployment configuration for an endpoint that hosts inference components. The configuration includes the desired deployment strategy and rollback settings.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-syntax.json"></a>

```
{
  "[AutoRollbackConfiguration](#cfn-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-autorollbackconfiguration)" : AutoRollbackConfiguration,
  "[RollingUpdatePolicy](#cfn-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-rollingupdatepolicy)" : InferenceComponentRollingUpdatePolicy
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-syntax.yaml"></a>

```
  [AutoRollbackConfiguration](#cfn-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-autorollbackconfiguration): 
    AutoRollbackConfiguration
  [RollingUpdatePolicy](#cfn-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-rollingupdatepolicy): 
    InferenceComponentRollingUpdatePolicy
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-properties"></a>

`AutoRollbackConfiguration`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-autorollbackconfiguration"></a>
Configuration for automatic rollback during inference component deployment.  
*Required*: No  
*Type*: [AutoRollbackConfiguration](aws-properties-sagemaker-inferencecomponent-autorollbackconfiguration.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`RollingUpdatePolicy`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentdeploymentconfig-rollingupdatepolicy"></a>
Specifies a rolling deployment strategy for updating a SageMaker AI endpoint.  
*Required*: No  
*Type*: [InferenceComponentRollingUpdatePolicy](aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentRollingUpdatePolicy
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy"></a>

Specifies a rolling deployment strategy for updating a SageMaker AI inference component.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-syntax.json"></a>

```
{
  "[MaximumBatchSize](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumbatchsize)" : InferenceComponentCapacitySize,
  "[MaximumExecutionTimeoutInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumexecutiontimeoutinseconds)" : Integer,
  "[RollbackMaximumBatchSize](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-rollbackmaximumbatchsize)" : InferenceComponentCapacitySize,
  "[WaitIntervalInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-waitintervalinseconds)" : Integer
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-syntax.yaml"></a>

```
  [MaximumBatchSize](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumbatchsize): 
    InferenceComponentCapacitySize
  [MaximumExecutionTimeoutInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumexecutiontimeoutinseconds): Integer
  [RollbackMaximumBatchSize](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-rollbackmaximumbatchsize): 
    InferenceComponentCapacitySize
  [WaitIntervalInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-waitintervalinseconds): Integer
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-properties"></a>

`MaximumBatchSize`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumbatchsize"></a>
The batch size for each rolling step in the deployment process. For each step, SageMaker AI provisions capacity on the new endpoint fleet, routes traffic to that fleet, and terminates capacity on the old endpoint fleet. The value must be between 5% to 50% of the copy count of the inference component.  
*Required*: No  
*Type*: [InferenceComponentCapacitySize](aws-properties-sagemaker-inferencecomponent-inferencecomponentcapacitysize.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`MaximumExecutionTimeoutInSeconds`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumexecutiontimeoutinseconds"></a>
The time limit for the total deployment. Exceeding this limit causes a timeout.  
*Required*: No  
*Type*: Integer  
*Minimum*: `600`  
*Maximum*: `28800`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`RollbackMaximumBatchSize`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-rollbackmaximumbatchsize"></a>
The batch size for a rollback to the old endpoint fleet. If this field is absent, the value is set to the default, which is 100% of the total capacity. When the default is used, SageMaker AI provisions the entire capacity of the old fleet at once during rollback.  
*Required*: No  
*Type*: [InferenceComponentCapacitySize](aws-properties-sagemaker-inferencecomponent-inferencecomponentcapacitysize.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`WaitIntervalInSeconds`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-waitintervalinseconds"></a>
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.  
*Required*: No  
*Type*: Integer  
*Minimum*: `0`  
*Maximum*: `3600`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentRuntimeConfig
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentruntimeconfig"></a>

Runtime settings for a model that is deployed with an inference component.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-syntax.json"></a>

```
{
  "[CopyCount](#cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-copycount)" : Integer,
  "[CurrentCopyCount](#cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-currentcopycount)" : Integer,
  "[DesiredCopyCount](#cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-desiredcopycount)" : Integer
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-syntax.yaml"></a>

```
  [CopyCount](#cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-copycount): Integer
  [CurrentCopyCount](#cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-currentcopycount): Integer
  [DesiredCopyCount](#cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-desiredcopycount): Integer
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-properties"></a>

`CopyCount`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-copycount"></a>
The number of runtime copies of the model container to deploy with the inference component. Each copy can serve inference requests.  
*Required*: No  
*Type*: Integer  
*Minimum*: `0`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`CurrentCopyCount`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-currentcopycount"></a>
The current number of copies of the model deployed for the inference component.  
*Required*: No  
*Type*: Integer  
*Minimum*: `0`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`DesiredCopyCount`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentruntimeconfig-desiredcopycount"></a>
The desired number of copies of the model to deploy for the inference component.  
*Required*: No  
*Type*: Integer  
*Minimum*: `0`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentSpecification
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentspecification"></a>

Details about the resources to deploy with this inference component, including the model, container, and compute resources.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentspecification-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentspecification-syntax.json"></a>

```
{
  "[BaseInferenceComponentName](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-baseinferencecomponentname)" : String,
  "[ComputeResourceRequirements](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-computeresourcerequirements)" : InferenceComponentComputeResourceRequirements,
  "[Container](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-container)" : InferenceComponentContainerSpecification,
  "[ModelName](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-modelname)" : String,
  "[StartupParameters](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-startupparameters)" : InferenceComponentStartupParameters
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentspecification-syntax.yaml"></a>

```
  [BaseInferenceComponentName](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-baseinferencecomponentname): String
  [ComputeResourceRequirements](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-computeresourcerequirements): 
    InferenceComponentComputeResourceRequirements
  [Container](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-container): 
    InferenceComponentContainerSpecification
  [ModelName](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-modelname): String
  [StartupParameters](#cfn-sagemaker-inferencecomponent-inferencecomponentspecification-startupparameters): 
    InferenceComponentStartupParameters
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentspecification-properties"></a>

`BaseInferenceComponentName`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentspecification-baseinferencecomponentname"></a>
The name of an existing inference component that is to contain the inference component that you're creating with your request.  
Specify this parameter only if your request is meant to create an adapter inference component. An adapter inference component contains the path to an adapter model. The purpose of the adapter model is to tailor the inference output of a base foundation model, which is hosted by the base inference component. The adapter inference component uses the compute resources that you assigned to the base inference component.  
When you create an adapter inference component, use the `Container` parameter to specify the location of the adapter artifacts. In the parameter value, use the `ArtifactUrl` parameter of the `InferenceComponentContainerSpecification` data type.  
Before you can create an adapter inference component, you must have an existing inference component that contains the foundation model that you want to adapt.  
*Required*: No  
*Type*: String  
*Pattern*: `^[a-zA-Z0-9](-*[a-zA-Z0-9])*$`  
*Maximum*: `63`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`ComputeResourceRequirements`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentspecification-computeresourcerequirements"></a>
The compute resources allocated to run the model, plus any adapter models, that you assign to the inference component.  
Omit this parameter if your request is meant to create an adapter inference component. An adapter inference component is loaded by a base inference component, and it uses the compute resources of the base inference component.  
*Required*: No  
*Type*: [InferenceComponentComputeResourceRequirements](aws-properties-sagemaker-inferencecomponent-inferencecomponentcomputeresourcerequirements.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`Container`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentspecification-container"></a>
Defines a container that provides the runtime environment for a model that you deploy with an inference component.  
*Required*: No  
*Type*: [InferenceComponentContainerSpecification](aws-properties-sagemaker-inferencecomponent-inferencecomponentcontainerspecification.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`ModelName`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentspecification-modelname"></a>
The name of an existing SageMaker AI model object in your account that you want to deploy with the inference component.  
*Required*: No  
*Type*: String  
*Pattern*: `^[a-zA-Z0-9](-*[a-zA-Z0-9])*$`  
*Maximum*: `63`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`StartupParameters`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentspecification-startupparameters"></a>
Settings that take effect while the model container starts up.  
*Required*: No  
*Type*: [InferenceComponentStartupParameters](aws-properties-sagemaker-inferencecomponent-inferencecomponentstartupparameters.md)  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent InferenceComponentStartupParameters
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentstartupparameters"></a>

Settings that take effect while the model container starts up.

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentstartupparameters-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentstartupparameters-syntax.json"></a>

```
{
  "[ContainerStartupHealthCheckTimeoutInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentstartupparameters-containerstartuphealthchecktimeoutinseconds)" : Integer,
  "[ModelDataDownloadTimeoutInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentstartupparameters-modeldatadownloadtimeoutinseconds)" : Integer
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentstartupparameters-syntax.yaml"></a>

```
  [ContainerStartupHealthCheckTimeoutInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentstartupparameters-containerstartuphealthchecktimeoutinseconds): Integer
  [ModelDataDownloadTimeoutInSeconds](#cfn-sagemaker-inferencecomponent-inferencecomponentstartupparameters-modeldatadownloadtimeoutinseconds): Integer
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-inferencecomponentstartupparameters-properties"></a>

`ContainerStartupHealthCheckTimeoutInSeconds`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentstartupparameters-containerstartuphealthchecktimeoutinseconds"></a>
The timeout value, in seconds, for your inference container to pass health check by Amazon S3 Hosting. For more information about health check, see [How Your Container Should Respond to Health Check (Ping) Requests](https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html#your-algorithms-inference-algo-ping-requests).  
*Required*: No  
*Type*: Integer  
*Minimum*: `60`  
*Maximum*: `3600`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`ModelDataDownloadTimeoutInSeconds`  <a name="cfn-sagemaker-inferencecomponent-inferencecomponentstartupparameters-modeldatadownloadtimeoutinseconds"></a>
The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this inference component.  
*Required*: No  
*Type*: Integer  
*Minimum*: `60`  
*Maximum*: `3600`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

# AWS::SageMaker::InferenceComponent Tag
<a name="aws-properties-sagemaker-inferencecomponent-tag"></a>

A tag object that consists of a key and an optional value, used to manage metadata for SageMaker AWS resources.

You can add tags to notebook instances, training jobs, hyperparameter tuning jobs, batch transform jobs, models, labeling jobs, work teams, endpoint configurations, and endpoints. For more information on adding tags to SageMaker resources, see [AddTags](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_AddTags.html).

For more information on adding metadata to your AWS resources with tagging, see [Tagging AWS resources](https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html). For advice on best practices for managing AWS resources with tagging, see [Tagging Best Practices: Implement an Effective AWS Resource Tagging Strategy](https://d1.awsstatic.com/whitepapers/aws-tagging-best-practices.pdf).

## Syntax
<a name="aws-properties-sagemaker-inferencecomponent-tag-syntax"></a>

To declare this entity in your CloudFormation template, use the following syntax:

### JSON
<a name="aws-properties-sagemaker-inferencecomponent-tag-syntax.json"></a>

```
{
  "[Key](#cfn-sagemaker-inferencecomponent-tag-key)" : String,
  "[Value](#cfn-sagemaker-inferencecomponent-tag-value)" : String
}
```

### YAML
<a name="aws-properties-sagemaker-inferencecomponent-tag-syntax.yaml"></a>

```
  [Key](#cfn-sagemaker-inferencecomponent-tag-key): String
  [Value](#cfn-sagemaker-inferencecomponent-tag-value): String
```

## Properties
<a name="aws-properties-sagemaker-inferencecomponent-tag-properties"></a>

`Key`  <a name="cfn-sagemaker-inferencecomponent-tag-key"></a>
The tag key. Tag keys must be unique per resource.  
*Required*: Yes  
*Type*: String  
*Minimum*: `1`  
*Maximum*: `128`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)

`Value`  <a name="cfn-sagemaker-inferencecomponent-tag-value"></a>
The tag value.  
*Required*: Yes  
*Type*: String  
*Minimum*: `1`  
*Maximum*: `256`  
*Update requires*: [No interruption](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-updating-stacks-update-behaviors.html#update-no-interrupt)