Documentation

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.

See: newProductionVariant smart constructor.

Create a value of ProductionVariant with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:acceleratorType:ProductionVariant', productionVariant_acceleratorType - 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.

$sel:containerStartupHealthCheckTimeoutInSeconds:ProductionVariant', productionVariant_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.

$sel:coreDumpConfig:ProductionVariant', productionVariant_coreDumpConfig - Specifies configuration for a core dump from the model container when the process crashes.

$sel:initialInstanceCount:ProductionVariant', productionVariant_initialInstanceCount - Number of instances to launch initially.

$sel:initialVariantWeight:ProductionVariant', productionVariant_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.

$sel:instanceType:ProductionVariant', productionVariant_instanceType - The ML compute instance type.

$sel:modelDataDownloadTimeoutInSeconds:ProductionVariant', productionVariant_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.

$sel:serverlessConfig:ProductionVariant', productionVariant_serverlessConfig - The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.

$sel:volumeSizeInGB:ProductionVariant', productionVariant_volumeSizeInGB - The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currenly only Amazon EBS gp2 storage volumes are supported.

$sel:variantName:ProductionVariant', productionVariant_variantName - The name of the production variant.

$sel:modelName:ProductionVariant', productionVariant_modelName - The name of the model that you want to host. This is the name that you specified when creating the model.

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.

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.

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

Number of instances to launch initially.

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.

The ML compute instance type.

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.

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

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

The name of the production variant.

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