VRAM usage

#34
by Yier48 - opened

When encoding long texts (tens of thousands of tokens) with a model, the required VRAM is too large—even a 48GB GPU is insufficient.
I would like to reduce VRAM usage by quantizing the model. Do you have any recommended methods?
Or are there other ways to reduce VRAM consumption?
Thanks!

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment