#include <caching_manager.h>
Inheritance diagram for tensorflow::serving::CachingManager:
Collaboration diagram for tensorflow::serving::CachingManager:
Classes | |
| class | LoaderFactory |
| struct | Options |
Public Member Functions | |
| std::map< ServableId, std::unique_ptr< UntypedServableHandle > > | GetAvailableUntypedServableHandles () const override |
| std::vector< ServableId > | ListAvailableServableIds () const override |
 Public Member Functions inherited from tensorflow::serving::Manager | |
| template<typename T > | |
| std::map< ServableId, ServableHandle< T > > | GetAvailableServableHandles () const |
| template<typename T > | |
| Status | GetServableHandle (const ServableRequest &request, ServableHandle< T > *const handle) |
Static Public Member Functions | |
| static Status | Create (Options options, std::unique_ptr< LoaderFactory > loader_factory, std::unique_ptr< CachingManager > *caching_manager) |
Friends | |
| class | test_util::CachingManagerTestAccess |
Detailed Description
A manager that manages and loads servables on-demand. Upon receiving the request for a servable name and optional version, the manager checks if it already has the requested servable loaded. If not, it initiates the load operation and then serves the request.
The manager blocks on the load operation and returns the handle when the servable has been loaded, or upon error.
Definition at line 45 of file caching_manager.h.
Member Function Documentation
◆ ListAvailableServableIds()
|
overridevirtual |
Gets a list of all available servable ids, i.e. each of these can be retrieved using GetServableHandle.
Implements tensorflow::serving::Manager.
Definition at line 199 of file caching_manager.cc.
The documentation for this class was generated from the following files:
- tensorflow_serving/core/caching_manager.h
- tensorflow_serving/core/caching_manager.cc
