View on GitHub
ProductionVariant Structure Reference
ProductionVariant
public struct ProductionVariant : AWSShapeUndocumented
-
Declaration
Swift
public static var _members: [AWSShapeMember] -
The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker.
Declaration
Swift
public let acceleratorType: ProductionVariantAcceleratorType? -
Number of instances to launch initially.
Declaration
Swift
public let initialInstanceCount: Int -
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 VariantWeight to the sum of all VariantWeight values across all ProductionVariants. If unspecified, it defaults to 1.0.
Declaration
Swift
public let initialVariantWeight: Float? -
The ML compute instance type.
Declaration
Swift
public let instanceType: ProductionVariantInstanceType -
The name of the model that you want to host. This is the name that you specified when creating the model.
Declaration
Swift
public let modelName: String -
The name of the production variant.
Declaration
Swift
public let variantName: String -
Undocumented
Declaration
Swift
public init(acceleratorType: ProductionVariantAcceleratorType? = nil, initialInstanceCount: Int, initialVariantWeight: Float? = nil, instanceType: ProductionVariantInstanceType, modelName: String, variantName: String) -
Declaration
Swift
public func validate(name: String) throws