Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefix caching in llama.cpp with PyTorch
#9
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Not glamorous advice, but repeatable baselines save a lot of time.

If you post your exact settings, people here can probably narrow it down pretty fast.
mostly local
Reply


Messages In This Thread
Re: prefix caching in llama.cpp with PyTorch - by macroforge - 10-10-2026, 08:35 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)