Package org.anchoranalysis.inference.concurrency

Specifying how many CPUs and GPUs can be allocated for some purpose.

See: Description

Interface Summary

Interface	Description
CreateModelForPool<T extends InferenceModel>	Creates a model to use in the pool.

Class Summary

Class	Description
ConcurrencyPlan	How many allocated CPUs and CPUs can be used concurrently for inference.
ConcurrentModel<T extends InferenceModel>	An instance of model that can be used concurrently for inference.
ConcurrentModelPool<T extends InferenceModel>	Keeps concurrent copies of a model to be used by different threads.
WithPriority<T>	Wraps an element of type T to ensure priority is given when the flag gpu==true.

Exception Summary

Exception	Description
ConcurrentModelException	This exception indicates that an error occurred when performing inference from a model concurrently.
CreateModelFailedException	When creating a model to be used for inference fails.

Package org.anchoranalysis.inference.concurrency Description

Specifying how many CPUs and GPUs can be allocated for some purpose.