Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
ROCm version that finally behaves for Gemma
#3
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Reply


Messages In This Thread
Re: ROCm version that finally behaves for Gemma - by dockworks23 - 10-17-2026, 08:29 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)