Channel INT8 for Deepseek v3.1 Terminus
#1
by
Doctor-Shotgun
- opened
Hey - thanks for these! I’ve been playing with CPU inference in sglang on the Xeon backend and these are the fastest quants that are supported.
Was wondering if you had plans to upload a Channel INT8 quant of the new v3.1 Terminus model?
EDIT: Intervitens did one, no longer needed
Doctor-Shotgun
changed discussion status to
closed