Transform model to be able to use Attention Sink
Pull Request resolved: https://github.com/pytorch/executorch/pull/6700 This PR adds necessary functions for transforming the model to be able to use Attention Sink. ghstack-source-id: 256108077 @exported-using-ghexport Differential Revision: [D65571289](https://our.internmc.facebook.com/intern/diff/D65571289/) Co-authored-by: Lunwen He <lwhecser@gmail.com>
P
pytorchbot committed
aa67cd91431c81b2012a698d6a95cca399fe2af7
Parent: e0eec82
Committed by GitHub <noreply@github.com>
on 12/2/2024, 11:35:44 PM