Package inference

Interface ModelConfigOuterClass.ModelRateLimiterOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
ModelConfigOuterClass.ModelRateLimiter, ModelConfigOuterClass.ModelRateLimiter.Builder
Enclosing class:
ModelConfigOuterClass

public static interface ModelConfigOuterClass.ModelRateLimiterOrBuilder extends com.google.protobuf.MessageOrBuilder
  • Method Details

    • getResourcesList

      @@  .. cpp:var:: Resource resources (repeated)
      @@
      @@     The resources required to execute the request on a model instance.
      @@     Resources are just names with a corresponding count. The execution
      @@     of the instance will be blocked until the specified resources are
      @@     available. By default an instance uses no rate-limiter resources.
      @@
       
      repeated .inference.ModelRateLimiter.Resource resources = 1;
    • getResources

      @@  .. cpp:var:: Resource resources (repeated)
      @@
      @@     The resources required to execute the request on a model instance.
      @@     Resources are just names with a corresponding count. The execution
      @@     of the instance will be blocked until the specified resources are
      @@     available. By default an instance uses no rate-limiter resources.
      @@
       
      repeated .inference.ModelRateLimiter.Resource resources = 1;
    • getResourcesCount

      int getResourcesCount()
      @@  .. cpp:var:: Resource resources (repeated)
      @@
      @@     The resources required to execute the request on a model instance.
      @@     Resources are just names with a corresponding count. The execution
      @@     of the instance will be blocked until the specified resources are
      @@     available. By default an instance uses no rate-limiter resources.
      @@
       
      repeated .inference.ModelRateLimiter.Resource resources = 1;
    • getResourcesOrBuilderList

      List<? extends ModelConfigOuterClass.ModelRateLimiter.ResourceOrBuilder> getResourcesOrBuilderList()
      @@  .. cpp:var:: Resource resources (repeated)
      @@
      @@     The resources required to execute the request on a model instance.
      @@     Resources are just names with a corresponding count. The execution
      @@     of the instance will be blocked until the specified resources are
      @@     available. By default an instance uses no rate-limiter resources.
      @@
       
      repeated .inference.ModelRateLimiter.Resource resources = 1;
    • getResourcesOrBuilder

      @@  .. cpp:var:: Resource resources (repeated)
      @@
      @@     The resources required to execute the request on a model instance.
      @@     Resources are just names with a corresponding count. The execution
      @@     of the instance will be blocked until the specified resources are
      @@     available. By default an instance uses no rate-limiter resources.
      @@
       
      repeated .inference.ModelRateLimiter.Resource resources = 1;
    • getPriority

      int getPriority()
      @@  .. cpp:var:: uint32 priority
      @@
      @@     The optional weighting value to be used for prioritizing across
      @@     instances. An instance with priority 2 will be given 1/2 the
      @@     number of scheduling chances as an instance_group with priority
      @@     1. The default priority is 1. The priority of value 0 will be
      @@     treated as priority 1.
      @@
       
      uint32 priority = 2;
      Returns:
      The priority.