david/flash-attention

réplica de https://github.com/Dao-AILab/flash-attention

Autor	SHA1 Mensaxe	Data
Tri Dao	0e8c46ae08 Run isort and black on test files	hai 1 ano
Tri Dao	88173a1aaf [FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP	hai 1 ano
Tri Dao	93383bd55b [TP] Implement TensorParallel without sequence parallel	hai 1 ano
Tri Dao	ef1ba918c6 [GPT] Refactor function to shard state_dict for TensorParallel	hai 1 ano
Tri Dao	b4018a5028 Implement Tensor Parallel for GPT model	%!s(int64=2) %!d(string=hai) anos