Struct aws_sdk_sagemaker::types::RecommendationMetrics

#[non_exhaustive]
pub struct RecommendationMetrics {
    pub cost_per_hour: Option<f32>,
    pub cost_per_inference: Option<f32>,
    pub max_invocations: Option<i32>,
    pub model_latency: Option<i32>,
    pub cpu_utilization: Option<f32>,
    pub memory_utilization: Option<f32>,
    pub model_setup_time: Option<i32>,
}

The metrics of recommendations.

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.

cost_per_hour: Option<f32>

Defines the cost per hour for the instance.

cost_per_inference: Option<f32>

Defines the cost per inference for the instance .

max_invocations: Option<i32>

The expected maximum number of requests per minute for the instance.

model_latency: Option<i32>

The expected model latency at maximum invocation per minute for the instance.

cpu_utilization: Option<f32>

The expected CPU utilization at maximum invocations per minute for the instance.

NaN indicates that the value is not available.

memory_utilization: Option<f32>

The expected memory utilization at maximum invocations per minute for the instance.

NaN indicates that the value is not available.

model_setup_time: Option<i32>

The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container.

NaN indicates that the value is not available.

Implementations

impl RecommendationMetrics

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

Defines the cost per hour for the instance.

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

Defines the cost per inference for the instance .

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

The expected maximum number of requests per minute for the instance.

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

The expected model latency at maximum invocation per minute for the instance.

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

The expected CPU utilization at maximum invocations per minute for the instance.

NaN indicates that the value is not available.

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

The expected memory utilization at maximum invocations per minute for the instance.

NaN indicates that the value is not available.

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

The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container.

NaN indicates that the value is not available.

impl RecommendationMetrics

pub fn builder() -> RecommendationMetricsBuilder

Creates a new builder-style object to manufacture RecommendationMetrics.

Trait Implementations

impl Clone for RecommendationMetrics

fn clone(&self) -> RecommendationMetrics

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for RecommendationMetrics

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

Formats the value using the given formatter.

impl PartialEq for RecommendationMetrics

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

Tests for self and other values to be equal, and is used by ==.

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

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

impl StructuralPartialEq for RecommendationMetrics