pulumi-gcp-kotlin/com.pulumi.gcp.vertex.kotlin.outputs/AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpec

AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpec

data class AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpec(val metricName: String, val target: Int? = null)

Constructors

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

Types

Link copied to clipboard
object Companion

Properties

Link copied to clipboard
val metricName: 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: 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.