Why does quantized tensor * 2 returns error?

[dalseeroh (Eugene Roh)]

I really appreciated your reply! However, I realized some FloatFunctional() ops are slower than FP32?

Slower ops in quantized::mul, quantized::cat

Hello, During quantization, I realized quantized operations such as quantized::mul, quantized::cat are x10 slower than fp32 ops. Is the only workaround wrapping those functions with dequant() and quant()? Please refer to the profiling below… FP32 Profiling (CPU) -------------------------------- ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ Name Self CPU % Self CPU CPU total % CPU tota…