pytorch

26a438d4 - Revert D16852280: Work around for bias quantization for conv and linear operators

Revert D16852280: Work around for bias quantization for conv and linear operators Test Plan: revert-hammer Differential Revision: D16852280 Original commit changeset: 988f8ff91616 fbshipit-source-id: e2cf03e13dc8dcf0db22d43740d72fd8b069fd74