Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
dual GPU split inference for Mistral
#3
Quote:Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.

That matches what I was seeing. That matches what I saw on 5090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Reply


Messages In This Thread
Re: dual GPU split inference for Mistral - by cudapoint - 08-31-2026, 09:22 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)