Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefix caching in llama.cpp for Phi
#3
Good point. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
2x3090 • llama.cpp • too much VRAM is still not enough
Reply


Messages In This Thread
Re: prefix caching in llama.cpp for Phi - by vrambandit - 10-07-2026, 05:49 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)