Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefix caching in llama.cpp with PyTorch
#4
Quote:following this because I'm in the same boat.

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. Not glamorous advice, but repeatable baselines save a lot of time.
2x3090 • llama.cpp • too much VRAM is still not enough
Reply


Messages In This Thread
Re: prefix caching in llama.cpp with PyTorch - by vrambandit - 10-07-2026, 07:11 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)