pytorch

703cfb00 - Fix floating point exception when nnz is zero for softmax backward cuda (#82341)

Fix floating point exception when nnz is zero for softmax backward cuda (#82341) Signed-off-by: Edward Z. Yang <ezyang@fb.com> Pull Request resolved: https://github.com/pytorch/pytorch/pull/82341 Approved by: https://github.com/cpuhrsch