Struct aws_sdk_sagemaker::model::production_variant::Builder

pub struct Builder { /* private fields */ }

A builder for ProductionVariant.

Implementations

impl Builder

pub fn variant_name(self, input: impl Into<String>) -> Self

The name of the production variant.

pub fn set_variant_name(self, input: Option<String>) -> Self

The name of the production variant.

pub fn model_name(self, input: impl Into<String>) -> Self

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

pub fn set_model_name(self, input: Option<String>) -> Self

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, input: i32) -> Self

Number of instances to launch initially.

pub fn set_initial_instance_count(self, input: Option<i32>) -> Self

Number of instances to launch initially.

pub fn instance_type(self, input: ProductionVariantInstanceType) -> Self

The ML compute instance type.

pub fn set_instance_type(
    self,
    input: Option<ProductionVariantInstanceType>
) -> Self

The ML compute instance type.

pub fn initial_variant_weight(self, input: f32) -> Self

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 set_initial_variant_weight(self, input: Option<f32>) -> Self

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, input: ProductionVariantAcceleratorType) -> Self

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 set_accelerator_type(
    self,
    input: Option<ProductionVariantAcceleratorType>
) -> Self

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, input: ProductionVariantCoreDumpConfig) -> Self

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

pub fn set_core_dump_config(
    self,
    input: Option<ProductionVariantCoreDumpConfig>
) -> Self

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

pub fn serverless_config(self, input: ProductionVariantServerlessConfig) -> Self

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

pub fn set_serverless_config(
    self,
    input: Option<ProductionVariantServerlessConfig>
) -> Self

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

pub fn volume_size_in_gb(self, input: i32) -> Self

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.

pub fn set_volume_size_in_gb(self, input: Option<i32>) -> Self

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.

pub fn model_data_download_timeout_in_seconds(self, input: i32) -> Self

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.

pub fn set_model_data_download_timeout_in_seconds(
    self,
    input: Option<i32>
) -> Self

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.

pub fn container_startup_health_check_timeout_in_seconds(
    self,
    input: i32
) -> Self

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.

pub fn set_container_startup_health_check_timeout_in_seconds(
    self,
    input: Option<i32>
) -> Self

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.

pub fn build(self) -> ProductionVariant

Consumes the builder and constructs a ProductionVariant.

Trait Implementations

impl Clone for Builder

fn clone(&self) -> Builder

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Builder

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

Formats the value using the given formatter.

impl Default for Builder

fn default() -> Builder

Returns the “default value” for a type.

impl PartialEq<Builder> for Builder

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

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

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

This method tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for Builder