lucidrains / local-attention

An implementation of local windowed attention for language modeling
MIT License
383 stars 40 forks source link

May I be allowed to delete einops and replace it with the operations provided by torch? #20

Closed wencan closed 4 months ago

wencan commented 8 months ago

May I be allowed to delete einops and replace it with the operations provided by torch? In this way, local-attention will only have one dependency: pytorch.

lucidrains commented 4 months ago

nope i like einops