Amazon SageMaker EndpointConfig ProductionVariant
The
ProductionVariant property type specifies a model that you want to host and
the resources to deploy for hosting it. If you are deploying multiple models, tell
Amazon
SageMaker how to distribute traffic among the models by specifying variant weights.
ProductionVariant is a property of the AWS::SageMaker::EndpointConfig resource.
Syntax
To declare this entity in your AWS CloudFormation template, use the following syntax:
JSON
{ "ModelName" :String, "VariantName" :String, "InitialInstanceCount" :Integer, "InstanceType" :String, "InitialVariantWeight" :Double, }
YAML
ModelName:StringVariantName:StringInitialInstanceCount:IntegerInstanceType:StringInitialVariantWeight:Double
Properties
ModelName-
The name of the model that you want to host.
Required: Yes
Type: String
Update requires: Replacement
VariantName-
The name of the production variant.
Required: Yes
Type: String
Update requires: Replacement
InitialInstanceCount-
The number of instances to launch initially for this production variant.
Required: Yes
Type: Integer
Update requires: Replacement
InstanceType-
The ML compute instance type to use for this production variant.
Required: Yes
Type: String
Update requires: Replacement
InitialVariantWeight-
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. The traffic to a production variant is determined by the ratio of the
VariantWeightto the sum of allVariantWeightvalues across all production variants for an endpoint. If unspecified, it defaults to 1.0.Required: Yes
Type: Double
Update requires: Replacement
