#[non_exhaustive]pub struct PendingProductionVariantSummary {
pub variant_name: Option<String>,
pub deployed_images: Option<Vec<DeployedImage>>,
pub current_weight: Option<f32>,
pub desired_weight: Option<f32>,
pub current_instance_count: Option<i32>,
pub desired_instance_count: Option<i32>,
pub instance_type: Option<ProductionVariantInstanceType>,
pub accelerator_type: Option<ProductionVariantAcceleratorType>,
pub variant_status: Option<Vec<ProductionVariantStatus>>,
pub current_serverless_config: Option<ProductionVariantServerlessConfig>,
pub desired_serverless_config: Option<ProductionVariantServerlessConfig>,
}
Expand description
The production variant summary for a deployment when an endpoint is creating or updating with the
or CreateEndpoint
operations. Describes the UpdateEndpoint
VariantStatus
, weight and capacity for a production variant associated with an endpoint.
Fields (Non-exhaustive)
This struct is marked as non-exhaustive
Struct { .. }
syntax; cannot be matched against without a wildcard ..
; and struct update syntax will not work.variant_name: Option<String>
The name of the variant.
deployed_images: Option<Vec<DeployedImage>>
An array of DeployedImage
objects that specify the Amazon EC2 Container Registry paths of the inference images deployed on instances of this ProductionVariant
.
current_weight: Option<f32>
The weight associated with the variant.
desired_weight: Option<f32>
The requested weight for the variant in this deployment, as specified in the endpoint configuration for the endpoint. The value is taken from the request to the
operation.CreateEndpointConfig
current_instance_count: Option<i32>
The number of instances associated with the variant.
desired_instance_count: Option<i32>
The number of instances requested in this deployment, as specified in the endpoint configuration for the endpoint. The value is taken from the request to the
operation.CreateEndpointConfig
instance_type: Option<ProductionVariantInstanceType>
The type of instances associated with the variant.
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.
variant_status: Option<Vec<ProductionVariantStatus>>
The endpoint variant status which describes the current deployment stage status or operational status.
current_serverless_config: Option<ProductionVariantServerlessConfig>
The serverless configuration for the endpoint.
Serverless Inference is in preview release for Amazon SageMaker and is subject to change. We do not recommend using this feature in production environments.
desired_serverless_config: Option<ProductionVariantServerlessConfig>
The serverless configuration requested for this deployment, as specified in the endpoint configuration for the endpoint.
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
The name of the variant.
An array of DeployedImage
objects that specify the Amazon EC2 Container Registry paths of the inference images deployed on instances of this ProductionVariant
.
The weight associated with the variant.
The requested weight for the variant in this deployment, as specified in the endpoint configuration for the endpoint. The value is taken from the request to the
operation.CreateEndpointConfig
The number of instances associated with the variant.
The number of instances requested in this deployment, as specified in the endpoint configuration for the endpoint. The value is taken from the request to the
operation.CreateEndpointConfig
The type of instances associated with the variant.
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 endpoint variant status which describes the current deployment stage status or operational status.
The serverless configuration for the endpoint.
Serverless Inference is in preview release for Amazon SageMaker and is subject to change. We do not recommend using this feature in production environments.
The serverless configuration requested for this deployment, as specified in the endpoint configuration for the endpoint.
Serverless Inference is in preview release for Amazon SageMaker and is subject to change. We do not recommend using this feature in production environments.
Creates a new builder-style object to manufacture PendingProductionVariantSummary
Trait Implementations
This method tests for self
and other
values to be equal, and is used
by ==
. Read more
This method tests for !=
.
Auto Trait Implementations
impl Send for PendingProductionVariantSummary
impl Sync for PendingProductionVariantSummary
impl Unpin for PendingProductionVariantSummary
Blanket Implementations
Mutably borrows from an owned value. Read more
Attaches the provided Subscriber
to this type, returning a
WithDispatch
wrapper. Read more
Attaches the current default Subscriber
to this type, returning a
WithDispatch
wrapper. Read more