ChooseQuantizationParams is not checking for min/max validity like Pytorch does
zhengwy888 opened this issue · comments
Weiyi Zheng commented
Hi, in Pytorch's ChooseQuantizationParams they check for min <= max
, but FBGEMM doesn't. This causes discrepancy in the behavior of pytorch code when compiled with USE_FBGEMM=1 and USE_FBGEMM=0. Can FBGEMM port this check over to make the behavior consistent?
Weiyi Zheng commented
cc @jspark1105 could you help ;-)