Inference › Hardware › GPUs v
dual GPU split inference

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
dual GPU split inference
rocmriley Offline
Member
***
Posts: 211
Threads: 21
Joined: Sep 2026
Reputation: 0
#2
10-09-2026, 08:44 AM
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
7900 XTX / ROCm / somehow still optimistic
Find
Reply


Messages In This Thread
dual GPU split inference - by turbogrid11 - 10-07-2026, 08:16 PM
Re: dual GPU split inference - by rocmriley - 10-09-2026, 08:44 AM
Re: dual GPU split inference - by paperrunner - 10-10-2026, 08:24 AM
Re: dual GPU split inference - by quantyard - 10-09-2026, 05:26 PM
Re: dual GPU split inference - by circuitwire58 - 10-09-2026, 07:51 PM
Re: dual GPU split inference - by amberhall - 10-10-2026, 09:25 AM
Re: dual GPU split inference - by vrambandit - 10-16-2026, 07:42 PM
Re: dual GPU split inference - by cudapoint - 10-17-2026, 05:12 AM
Re: dual GPU split inference - by mintquill - 10-13-2026, 09:37 AM
Re: dual GPU split inference - by paperrunner - 10-16-2026, 09:47 AM
Re: dual GPU split inference - by turbogrid11 - 10-16-2026, 10:36 AM
Re: dual GPU split inference - by signaltrack44 - 10-16-2026, 10:56 AM
Re: dual GPU split inference - by amberhall - 10-16-2026, 08:51 PM
Re: dual GPU split inference - by fusedhall - 10-18-2026, 05:13 PM
Re: dual GPU split inference - by sparrowcraft - 10-18-2026, 09:59 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)