fp8 fmt for hopper ep deploy?

#98

by whybeyoung - opened Mar 4

Mar 4

we wan to deploy k2.5 with p/d disaggregation deploy , which decode deploy as ep16 on hopper series... do we have fp8 fmt ?

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