Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::AutoscalingMetricSpec (v0.31.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::AutoscalingMetricSpec.

The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#metric_name

def metric_name() -> ::String
Returns
  • (::String) —

    Required. The resource metric name. Supported metrics:

    • For Online Prediction:
    • aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
    • aiplatform.googleapis.com/prediction/online/cpu/utilization

#metric_name=

def metric_name=(value) -> ::String
Parameter
  • value (::String) —

    Required. The resource metric name. Supported metrics:

    • For Online Prediction:
    • aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
    • aiplatform.googleapis.com/prediction/online/cpu/utilization
Returns
  • (::String) —

    Required. The resource metric name. Supported metrics:

    • For Online Prediction:
    • aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
    • aiplatform.googleapis.com/prediction/online/cpu/utilization

#target

def target() -> ::Integer
Returns
  • (::Integer) — 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.

#target=

def target=(value) -> ::Integer
Parameter
  • value (::Integer) — 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.
Returns
  • (::Integer) — 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.