Define QNN_PROPERTY_TENSOR_SUPPORT_QUANTIZATION_ENCODING_MICROSCALING

• Defined in File QnnProperty.h

Define Documentation

QNN_PROPERTY_TENSOR_SUPPORT_QUANTIZATION_ENCODING_MICROSCALING (QNN_PROPERTY_GROUP_TENSOR + 32)

Property key to determine whether a backend supports Microscaling quantization encodings. See QNN_QUANTIZATION_ENCODING_MICROSCALING.