Cloud AI Platform v1beta1 API - Class AutomaticResources (1.0.0-beta04)

public sealed class AutomaticResources : IMessage<AutomaticResources>, IEquatable<AutomaticResources>, IDeepCloneable<AutomaticResources>, IBufferMessage, IMessage

Reference documentation and code samples for the Cloud AI Platform v1beta1 API class AutomaticResources.

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines.

Inheritance

object > AutomaticResources

Namespace

Google.Cloud.AIPlatform.V1Beta1

Assembly

Google.Cloud.AIPlatform.V1Beta1.dll

Constructors

AutomaticResources()

public AutomaticResources()

AutomaticResources(AutomaticResources)

public AutomaticResources(AutomaticResources other)
Parameter
Name Description
other AutomaticResources

Properties

MaxReplicaCount

public int MaxReplicaCount { get; set; }

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, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.

Property Value
Type Description
int

MinReplicaCount

public int MinReplicaCount { get; set; }

Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to [max_replica_count][google.cloud.aiplatform.v1beta1.AutomaticResources.max_replica_count], and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.

Property Value
Type Description
int