8-bit quantization

by amarosnithe - opened Apr 8

Apr 8

Hi, could you guys (or anyone) quantize this to fp8? The ones that've been done so far are only for MLX (so I can't run them as a Windows user).

Looks like people did, thanks guys!

amarosnithe changed discussion status to closed 7 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment