max_pool2d cuda should have channel last optimized kernels[Performance improvement] (#24872)
Summary:
max_pool2d_with_indices_cuda and max_pool2d_with_indices_backward_cuda should have channel last optimized kernels(https://github.com/pytorch/pytorch/issues/23815)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/24872
Differential Revision: D16964577
Pulled By: ifedan
fbshipit-source-id: 296dfef8e511a7ae2ed423e34e902d5401b3becb
