Enum Qnn_Precision_t

Enum Documentation

enum Qnn_Precision_t

An enum which defines the different precision modes supported by QNN backends. A precision mode may be used to express the math type used in the implementation of an operation.

Values:

enumerator QNN_PRECISION_FLOAT32 = 0

32-bit Floating point precision. The format of the floating point value is left to backends to choose.

enumerator QNN_PRECISION_FLOAT16 = 1

16-bit Floating point precision. The format of the floating point value is left to backends to choose.

enumerator QNN_PRECISION_UNDEFINED = 0x7FFFFFFF