Is it possible to convert or quantize fp32 onnx file to fp16, int8 dlc file with snpe or qnn binary program?
I already succeeded converting llama2-7b-fp32 to llama2-7b-ufxp8, however, I want to convert llama2-7b-fp32 to fp16 or int8, not unsigned fixed point(uFxp 8 or 16). Is it possible?
Data type
Posted: Sun, 2024-07-14 05:51