ProductionVariant

import type { ProductionVariant } from "https://aws-api.deno.dev/v0.3/services/sagemaker.ts?docs=full";

Identifies a model that you want to host and the resources chosen to deploy for hosting it. If you are deploying multiple models, tell Amazon SageMaker how to distribute traffic among the models by specifying variant weights.

interface ProductionVariant {

AcceleratorType?: ProductionVariantAcceleratorType | null;

CoreDumpConfig?: ProductionVariantCoreDumpConfig | null;

InitialInstanceCount?: number | null;

InitialVariantWeight?: number | null;

InstanceType?: ProductionVariantInstanceType | null;

ModelName: string;

ServerlessConfig?: ProductionVariantServerlessConfig | null;

VariantName: string;

}

§Properties

AcceleratorType?: ProductionVariantAcceleratorType | null

[src]

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.

CoreDumpConfig?: ProductionVariantCoreDumpConfig | null

[src]

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

InitialInstanceCount?: number | null

[src]

Number of instances to launch initially.

InitialVariantWeight?: number | null

[src]

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.

InstanceType?: ProductionVariantInstanceType | null

[src]

The ML compute instance type.

ModelName: string

[src]

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

ServerlessConfig?: ProductionVariantServerlessConfig | null

[src]

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

Note: Serverless Inference is in preview release for Amazon SageMaker and is subject to change. We do not recommend using this feature in production environments.

VariantName: string

[src]

The name of the production variant.