Struct aws_sdk_sagemaker::model::ProductionVariant

#[non_exhaustive]
pub struct ProductionVariant {
    pub variant_name: Option<String>,
    pub model_name: Option<String>,
    pub initial_instance_count: Option<i32>,
    pub instance_type: Option<ProductionVariantInstanceType>,
    pub initial_variant_weight: Option<f32>,
    pub accelerator_type: Option<ProductionVariantAcceleratorType>,
    pub core_dump_config: Option<ProductionVariantCoreDumpConfig>,
    pub serverless_config: Option<ProductionVariantServerlessConfig>,
}

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.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

variant_name: Option<String>

The name of the production variant.

model_name: Option<String>

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

initial_instance_count: Option<i32>

Number of instances to launch initially.

instance_type: Option<ProductionVariantInstanceType>

The ML compute instance type.

initial_variant_weight: Option<f32>

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.

accelerator_type: Option<ProductionVariantAcceleratorType>

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.

core_dump_config: Option<ProductionVariantCoreDumpConfig>

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

serverless_config: Option<ProductionVariantServerlessConfig>

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

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

Implementations

impl ProductionVariant

pub fn variant_name(&self) -> Option<&str>

The name of the production variant.

pub fn model_name(&self) -> Option<&str>

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

pub fn initial_instance_count(&self) -> Option<i32>

Number of instances to launch initially.

pub fn instance_type(&self) -> Option<&ProductionVariantInstanceType>

The ML compute instance type.

pub fn initial_variant_weight(&self) -> Option<f32>

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.

pub fn accelerator_type(&self) -> Option<&ProductionVariantAcceleratorType>

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.

pub fn core_dump_config(&self) -> Option<&ProductionVariantCoreDumpConfig>

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

pub fn serverless_config(&self) -> Option<&ProductionVariantServerlessConfig>

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

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

impl ProductionVariant

pub fn builder() -> Builder

Creates a new builder-style object to manufacture ProductionVariant

Trait Implementations

impl Clone for ProductionVariant

fn clone(&self) -> ProductionVariant

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ProductionVariant

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq<ProductionVariant> for ProductionVariant

fn eq(&self, other: &ProductionVariant) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &ProductionVariant) -> bool

This method tests for !=.

impl StructuralPartialEq for ProductionVariant