interesting new finetuning approach from stanford - ReFT

[fblissjr]

https://github.com/stanfordnlp/pyreft

uses flash attn and pyvene (https://github.com/stanfordnlp/pyvene) but don't see any specific kernels aside from flashattn. tried this on my cuda machine and it's neat - not sure how effective at scale yet, but worth exploring. anyone else looking into this?