sagemaker/aws.sdk.kotlin.services.sagemaker.model/RecommendationMetrics

RecommendationMetrics

class RecommendationMetrics

The metrics of recommendations.

Types

object Companion

Properties

val costPerHour: Float?

Defines the cost per hour for the instance.

costPerInference

val costPerInference: Float?

Defines the cost per inference for the instance .

val cpuUtilization: Float?

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

val maxInvocations: Int?

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

memoryUtilization

val memoryUtilization: Float?

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

val modelLatency: Int?

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

val modelSetupTime: Int?

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.

Functions

inline fun copy(block: RecommendationMetrics.Builder.() -> Unit = {}): RecommendationMetrics

open operator override fun equals(other: Any?): Boolean

open override fun hashCode(): Int

open override fun toString(): String