jjsjann123 692ebc8d8b baby steps on patching inf/nan behavior & aten::amin support in nvfuser ... Fixes #75622 1. Instead of getting max/min_value for reduction init value, we go with (-)infinity instead so we can properly preserve inf inputs; 2. Adding inf/(-)inf/nan for float value. 3. Adding aten::amin in nvfuser (@kevinstephano @rdspring1 for review) Pull Request resolved: https://github.com/pytorch/pytorch/pull/75646 Approved by: https://github.com/rdspring1, https://github.com/kevinstephano, https://github.com/ngimel		2022-04-13 15:51:17 +00:00
..
cuda	baby steps on patching inf/nan behavior & aten::amin support in nvfuser	2022-04-13 15:51:17 +00:00
fuser	Enable win-arm64	2022-02-28 17:17:56 +00:00