Interface IInstanceProductionVariantProps
(experimental) Construction properties for an instance production variant.
Namespace: Amazon.CDK.AWS.Sagemaker.Alpha
Assembly: Amazon.CDK.AWS.Sagemaker.Alpha.dll
Syntax (csharp)
public interface IInstanceProductionVariantProps
Syntax (vb)
Public Interface IInstanceProductionVariantProps
Remarks
Stability: Experimental
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.Alpha;
AcceleratorType acceleratorType;
InstanceType instanceType;
Model model;
var instanceProductionVariantProps = new InstanceProductionVariantProps {
Model = model,
VariantName = "variantName",
// the properties below are optional
AcceleratorType = acceleratorType,
InitialInstanceCount = 123,
InitialVariantWeight = 123,
InstanceType = instanceType
};
Synopsis
Properties
AcceleratorType | (experimental) The size of the Elastic Inference (EI) instance to use for the production variant. |
InitialInstanceCount | (experimental) Number of instances to launch initially. |
InitialVariantWeight | (experimental) Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. |
InstanceType | (experimental) Instance type of the production variant. |
Model | (experimental) The model to host. |
VariantName | (experimental) Name of the production variant. |
Properties
AcceleratorType
(experimental) The size of the Elastic Inference (EI) instance to use for the production variant.
virtual AcceleratorType AcceleratorType { get; }
Property Value
Remarks
EI instances provide on-demand GPU computing for inference.
Default: - none
Stability: Experimental
InitialInstanceCount
(experimental) Number of instances to launch initially.
virtual Nullable<double> InitialInstanceCount { get; }
Property Value
System.Nullable<System.Double>
Remarks
Default: 1
Stability: Experimental
InitialVariantWeight
(experimental) Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
virtual Nullable<double> InitialVariantWeight { get; }
Property Value
System.Nullable<System.Double>
Remarks
The traffic to a production variant is determined by the ratio of the variant weight to the sum of all variant weight values across all production variants.
Default: 1.0
Stability: Experimental
InstanceType
(experimental) Instance type of the production variant.
virtual InstanceType InstanceType { get; }
Property Value
Remarks
Default: InstanceType.T2_MEDIUM
Stability: Experimental
Model
(experimental) The model to host.
IModel Model { get; }
Property Value
Remarks
Stability: Experimental
VariantName
(experimental) Name of the production variant.
string VariantName { get; }
Property Value
System.String
Remarks
Stability: Experimental