Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1DedicatedResources

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb

Overview

A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1DedicatedResources

Returns a new instance of GoogleCloudAiplatformV1DedicatedResources.



5284
5285
5286
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5284

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#autoscaling_metric_specs ⇒ Array<Google::Apis::AiplatformV1::GoogleCloudAiplatformV1AutoscalingMetricSpec>

Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value ( default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80. Corresponds to the JSON property autoscalingMetricSpecs

Returns:



5236
5237
5238
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5236

def autoscaling_metric_specs
  @autoscaling_metric_specs
end

#machine_spec ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1MachineSpec

Specification of a single machine. Corresponds to the JSON property machineSpec

Returns:



5241
5242
5243
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5241

def machine_spec
  @machine_spec
end

#max_replica_count ⇒ Fixnum

Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type). Corresponds to the JSON property maxReplicaCount

Returns:

  • (Fixnum) 


5256
5257
5258
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5256

def max_replica_count
  @max_replica_count
end

#min_replica_count ⇒ Fixnum

Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed. Corresponds to the JSON property minReplicaCount

Returns:

  • (Fixnum) 


5265
5266
5267
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5265

def min_replica_count
  @min_replica_count
end

#required_replica_count ⇒ Fixnum

Optional. Number of required available replicas for the deployment to succeed. This field is only needed when partial model deployment/mutation is desired. If set, the model deploy/mutate operation will succeed once available_replica_count reaches required_replica_count, and the rest of the replicas will be retried. If not set, the default required_replica_count will be min_replica_count. Corresponds to the JSON property requiredReplicaCount

Returns:

  • (Fixnum) 


5275
5276
5277
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5275

def required_replica_count
  @required_replica_count
end

#spot ⇒ Boolean Also known as: spot?

Optional. If true, schedule the deployment workload on spot VMs. Corresponds to the JSON property spot

Returns:

  • (Boolean) 


5281
5282
5283
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5281

def spot
  @spot
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



5289
5290
5291
5292
5293
5294
5295
5296
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 5289

def update!(**args)
  @autoscaling_metric_specs = args[:autoscaling_metric_specs] if args.key?(:autoscaling_metric_specs)
  @machine_spec = args[:machine_spec] if args.key?(:machine_spec)
  @max_replica_count = args[:max_replica_count] if args.key?(:max_replica_count)
  @min_replica_count = args[:min_replica_count] if args.key?(:min_replica_count)
  @required_replica_count = args[:required_replica_count] if args.key?(:required_replica_count)
  @spot = args[:spot] if args.key?(:spot)
end