09-03-2026, 04:23 PM
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
|
dual GPU split inference
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
dual GPU split inference - by routecrate - 09-02-2026, 04:05 AM
Re: dual GPU split inference - by amberhall - 09-03-2026, 04:23 PM
Re: dual GPU split inference - by cudapoint - 09-03-2026, 04:33 PM
|
Users browsing this thread: 1 Guest(s)