[cpu] implement flash attention backward (#104693)
Feature RFC: https://github.com/pytorch/rfcs/pull/56.
The flash attention CPU kernel is added, for backward path FP32. Parallelization is on the dimensions of batch size and head number.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/104693
Approved by: https://github.com/jgong5, https://github.com/drisspg
ghstack dependencies: #104583, #104584, #103826
