Experimental
@aws-cdk/aws-sagemaker-alpha is an experimental (alpha) package: its API may change in any release, without a major version bump.
ServerlessProductionVariantProps Struct
Construction properties for a serverless production variant.
| Stability | Experimental |
|---|---|
| Source | lib/endpoint-config.ts |
Example
ts
import * as sagemaker from '@aws-cdk/aws-sagemaker-alpha';
declare const model: sagemaker.Model;
const endpointConfig = new sagemaker.EndpointConfig(this, 'ServerlessEndpointConfig', {
serverlessProductionVariant: {
model: model,
variantName: 'serverlessVariant',
maxConcurrency: 10,
memorySizeInMB: 2048,
provisionedConcurrency: 5, // optional
},
});
python
import aws_cdk.aws_sagemaker_alpha as sagemaker
# model: sagemaker.Model
endpoint_config = sagemaker.EndpointConfig(self, "ServerlessEndpointConfig",
serverless_production_variant=sagemaker.ServerlessProductionVariantProps(
model=model,
variant_name="serverlessVariant",
max_concurrency=10,
memory_size_in_mb=2048,
provisioned_concurrency=5
)
)
java
import software.amazon.awscdk.services.sagemaker.alpha.*;
Model model;
EndpointConfig endpointConfig = EndpointConfig.Builder.create(this, "ServerlessEndpointConfig")
.serverlessProductionVariant(ServerlessProductionVariantProps.builder()
.model(model)
.variantName("serverlessVariant")
.maxConcurrency(10)
.memorySizeInMB(2048)
.provisionedConcurrency(5)
.build())
.build();
csharp
// Install: dotnet add package Amazon.CDK.AWS.Sagemaker.Alpha
using Amazon.CDK.AWS.Sagemaker.Alpha;
Model model;
var endpointConfig = new EndpointConfig(this, "ServerlessEndpointConfig", new EndpointConfigProps {
ServerlessProductionVariant = new ServerlessProductionVariantProps {
Model = model,
VariantName = "serverlessVariant",
MaxConcurrency = 10,
MemorySizeInMB = 2048,
ProvisionedConcurrency = 5
}
});
go
// Install: go get github.com/aws/aws-cdk-go/awscdksagemakeralpha/v2
import sagemaker "github.com/aws/aws-cdk-go/awscdksagemakeralpha"
var model Model
endpointConfig := sagemaker.NewEndpointConfig(this, jsii.String("ServerlessEndpointConfig"), &EndpointConfigProps{
ServerlessProductionVariant: &ServerlessProductionVariantProps{
Model: model,
VariantName: jsii.String("serverlessVariant"),
MaxConcurrency: jsii.Number(10),
MemorySizeInMB: jsii.Number(2048),
ProvisionedConcurrency: jsii.Number(5),
},
})
Properties
initialVariantWeightoptionalnumberinitial_variant_weightoptionalint | floatinitialVariantWeightoptionalNumberInitialVariantWeightoptionaldoubleInitialVariantWeightoptional*float64 = 1.0 #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 variant weight to the sum of all variant weight values across all production variants.
maxConcurrencynumbermax_concurrencyint | floatmaxConcurrencyNumberMaxConcurrencydoubleMaxConcurrency*float64 required #The maximum number of concurrent invocations your serverless endpoint can process.
Valid range: 1-200
memorySizeInMBnumbermemory_size_in_mbint | floatmemorySizeInMBNumberMemorySizeInMBdoubleMemorySizeInMB*float64 required #The memory size of your serverless endpoint.
Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
provisionedConcurrencyoptionalnumberprovisioned_concurrencyoptionalint | floatprovisionedConcurrencyoptionalNumberProvisionedConcurrencyoptionaldoubleProvisionedConcurrencyoptional*float64 = none #The number of concurrent invocations that are provisioned and ready to respond to your endpoint.
Valid range: 1-200, must be less than or equal to maxConcurrency.
Name of the production variant.