Enum TfLiteQnnDelegateBackendType¶
Defined in File QnnTFLiteDelegate.h
Enum Documentation¶
-
enum TfLiteQnnDelegateBackendType
The QNN backend used to delegate the model’s nodes. Each backend has its own set of supported ops and tensor types.
Values:
-
enumerator kUndefinedBackend = 0¶
-
enumerator kGpuBackend¶
Backend for AdrenoTM GPU hardware accelerator.
-
enumerator kHtpBackend¶
Backend for Hexagon HTP hardware accelerator.
-
enumerator kDspBackend¶
Backend for Hexagon DSP hardware accelerator.
-
enumerator kUndefinedBackend = 0¶