pytorch

1871d4e6 - avoid explicitly casting low precision inputs to fp32 in norm (#59134)

avoid explicitly casting low precision inputs to fp32 in norm (#59134) Summary: Per title. Now `norm` with fp16/bfloat16 inputs and fp32 outputs on cuda won't do explicit cast Pull Request resolved: https://github.com/pytorch/pytorch/pull/59134 Reviewed By: mruberry Differential Revision: D28775729 Pulled By: ngimel fbshipit-source-id: 896daa4f02e8a817cb7cb99ae8a93c02fa8dd5e9