ProductionVariant

Identifies a model that you want to host and the resources chosen to deploy for hosting it. If you are deploying multiple models, tell SageMaker how to distribute traffic among the models by specifying variant weights. For more information on production variants, check Production variants.

VariantName

The name of the production variant.

Type: String

Length Constraints: Minimum length of 0. Maximum length of 63.

Pattern: [a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}

Required: Yes

AcceleratorType

This parameter is no longer supported. Elastic Inference (EI) is no longer available.

This parameter was used to specify the size of the EI instance to use for the production variant.

Type: String

Required: No

CapacityReservationConfig

Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.

Type: ProductionVariantCapacityReservationConfig object

Required: No

ContainerStartupHealthCheckTimeoutInSeconds

The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests.

Type: Integer

Valid Range: Minimum value of 60. Maximum value of 3600.

Required: No

CoreDumpConfig

Specifies configuration for a core dump from the model container when the process crashes.

Type: ProductionVariantCoreDumpConfig object

Required: No

EnableSSMAccess

You can use this parameter to turn on native Amazon Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint. You can turn on or turn off SSM access for a production variant behind an existing endpoint by creating a new endpoint configuration and calling UpdateEndpoint.

Type: Boolean

Required: No

InferenceAmiVersion

Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by Amazon with a set of software and driver versions. Amazon optimizes these configurations for different machine learning workloads.

By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Neuron driver versions.

The AMI version names, and their configurations, are the following:

al2-ami-sagemaker-inference-gpu-2

Accelerator: GPU
NVIDIA driver version: 535
CUDA version: 12.2

al2-ami-sagemaker-inference-gpu-2-1

Accelerator: GPU
NVIDIA driver version: 535
CUDA version: 12.2
NVIDIA Container Toolkit with disabled CUDA-compat mounting

al2-ami-sagemaker-inference-gpu-3-1

Accelerator: GPU
NVIDIA driver version: 550
CUDA version: 12.4
NVIDIA Container Toolkit with disabled CUDA-compat mounting

al2-ami-sagemaker-inference-neuron-2

Accelerator: Inferentia2 and Trainium
Neuron driver version: 2.19

Type: String

Valid Values: al2-ami-sagemaker-inference-gpu-2 | al2-ami-sagemaker-inference-gpu-2-1 | al2-ami-sagemaker-inference-gpu-3-1 | al2-ami-sagemaker-inference-neuron-2

Required: No

InitialInstanceCount

Number of instances to launch initially.

Type: Integer

Valid Range: Minimum value of 1.

Required: No

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 VariantWeight to the sum of all VariantWeight values across all ProductionVariants. If unspecified, it defaults to 1.0.

Type: Float

Valid Range: Minimum value of 0.

Required: No

InstanceType

The ML compute instance type.

Type: String

Required: No

ManagedInstanceScaling

Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.

Type: ProductionVariantManagedInstanceScaling object

Required: No

ModelDataDownloadTimeoutInSeconds

The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.

Type: Integer

Valid Range: Minimum value of 60. Maximum value of 3600.

Required: No

ModelName

The name of the model that you want to host. This is the name that you specified when creating the model.

Type: String

Length Constraints: Minimum length of 0. Maximum length of 63.

Pattern: [a-zA-Z0-9]([\-a-zA-Z0-9]*[a-zA-Z0-9])?

Required: No

RoutingConfig

Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.

Type: ProductionVariantRoutingConfig object

Required: No

ServerlessConfig

The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.

Type: ProductionVariantServerlessConfig object

Required: No

VolumeSizeInGB

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

Type: Integer

Valid Range: Minimum value of 1. Maximum value of 512.

Required: No

ProductionVariant

Contents

See Also