All Classes and Interfaces

Class	Description
Adapter	An adapter is a modification producing a variation of a model that can be used during prediction.
Job<I,O>	A class represents an inference job.
JobFunction<I,O>	A function describing the action to take in a Job.
LmiUtils	A utility class to detect optimal engine for LMI model.
ModelInfo<I,O>	A class represent a loaded model and it's metadata.
PermanentBatchAggregator<I,O>	a batch aggregator that never terminates by itself.
PyAdapter	An overload of Adapter for the python engine.
SageMakerUtils	A utility class to detect optimal engine for SageMaker saved model.
TemporaryBatchAggregator<I,O>	a batch aggregator that terminates after a maximum idle time.
WlmCapacityException	Thrown to throttle when a job is run but the job queue capacity is exceeded.
WlmConfigManager	This manages some configurations used by the WorkLoadManager.
WlmException	Thrown when an exception occurs inside the WorkLoadManager.
WlmOutOfMemoryException	Thrown when no enough memory to load the model.
WlmShutdownException	Thrown when a job is run but all workers are shutdown.
WorkerGroup<I,O>	The WorkerGroup manages the WorkerPool for a particular Device.
WorkerIdGenerator	class to generate an unique worker id.
WorkerJob<I,O>	A Job containing metadata from the WorkLoadManager.
WorkerPool<I,O>	Manages the work load for a single model.
WorkerPoolConfig<I,O>	A WorkerPoolConfig represents a task that could be run in the WorkLoadManager.
WorkerPoolConfig.Status	An enum represents state of a worker type.
WorkerPoolConfig.ThreadConfig<I,O>	The part of the WorkerPoolConfig for an individual WorkerThread.
WorkerState	An enum represents state of a worker.
WorkerThread<I,O>	The WorkerThread is the worker managed by the WorkLoadManager.
WorkerThread.Builder<I,O>	A Builder to construct a WorkerThread.
WorkLoadManager	WorkLoadManager is responsible to manage the work load of worker thread.