pulumi-gcp-kotlin/com.pulumi.gcp.vertex.kotlin.inputs/AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs

AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs

data class AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs(val metricName: Output<String>, val target: Output<Int>? = null) : ConvertibleToJava<AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs>

Constructors

constructor(metricName: Output<String>, target: Output<Int>? = null)

Properties

Link copied to clipboard
val metricName: Output<String>

The resource metric name. Supported metrics: For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization

Link copied to clipboard
val target: Output<Int>? = null

The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.

Functions

Link copied to clipboard
open override fun toJava(): AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs