enable gguf

#3
by ehartford - opened

hello @francislabounty
Can you please enable gguf?
I would really like to try sparsetral.
https://github.com/ggerganov/llama.cpp/issues/5365

GPTQ and AWQ too, I imagine changes need to be made to upstream for it to work

It's interesting that exl2 just supported it out of the box

Sign up or log in to comment