AWS::SageMaker::ModelPackage AdditionalInferenceSpecificationDefinition
A structure of additional Inference Specification. Additional Inference Specification specifies details about inference jobs that can be run with models based on this model package
Syntax
To declare this entity in your Amazon CloudFormation template, use the following syntax:
JSON
{ "Containers" :
[ ModelPackageContainerDefinition, ... ]
, "Description" :String
, "Name" :String
, "SupportedContentTypes" :[ String, ... ]
, "SupportedRealtimeInferenceInstanceTypes" :[ String, ... ]
, "SupportedResponseMIMETypes" :[ String, ... ]
, "SupportedTransformInstanceTypes" :[ String, ... ]
}
YAML
Containers:
- ModelPackageContainerDefinition
Description:String
Name:String
SupportedContentTypes:- String
SupportedRealtimeInferenceInstanceTypes:- String
SupportedResponseMIMETypes:- String
SupportedTransformInstanceTypes:- String
Properties
Containers
-
The Amazon ECR registry path of the Docker image that contains the inference code.
Required: Yes
Type: Array of ModelPackageContainerDefinition
Minimum:
1
Maximum:
15
Update requires: No interruption
Description
-
A description of the additional Inference specification
Required: No
Type: String
Pattern:
.*
Maximum:
1024
Update requires: No interruption
Name
-
A unique name to identify the additional inference specification. The name must be unique within the list of your additional inference specifications for a particular model package.
Required: Yes
Type: String
Pattern:
^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}$
Minimum:
1
Maximum:
63
Update requires: No interruption
SupportedContentTypes
-
The supported MIME types for the input data.
Required: No
Type: Array of String
Update requires: No interruption
SupportedRealtimeInferenceInstanceTypes
-
A list of the instance types that are used to generate inferences in real-time.
Required: No
Type: Array of String
Update requires: No interruption
SupportedResponseMIMETypes
-
The supported MIME types for the output data.
Required: No
Type: Array of String
Update requires: No interruption
SupportedTransformInstanceTypes
-
A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.
Required: No
Type: Array of String
Minimum:
1
Update requires: No interruption