Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
dual GPU split inference
#1
This keeps coming up in conversation so I figured I'd start a thread.

One thing I keep noticing is that people underestimate HBM constraints until they actually try to run this stuff for more than one afternoon.

Curious whether that lines up with what other people are seeing.
2x3090 • llama.cpp • too much VRAM is still not enough
Reply


Messages In This Thread
dual GPU split inference - by vrambandit - 10-14-2026, 11:10 AM
Re: dual GPU split inference - by fusedhall - 10-15-2026, 11:18 PM
Re: dual GPU split inference - by sanevault - 10-18-2026, 07:38 PM
Re: dual GPU split inference - by quietstack - 10-16-2026, 11:23 PM
Re: dual GPU split inference - by benchplease - 10-18-2026, 11:59 AM
Re: dual GPU split inference - by fusedhall - 10-18-2026, 05:20 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)