Class AutomaticResources (0.5.1)

AutomaticResources(mapping=None, *, ignore_unknown_fields=False, **kwargs)

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

Attributes

Name Description
min_replica_count int
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``, and as traffic decreases, some of these extra replicas may be freed. If requested value is too large, the deployment will error.
max_replica_count int
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If 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 AI Platform may be unable to scale beyond certain replica number.

Inheritance

builtins.object > proto.message.Message > AutomaticResources