Inference › Inference Engines › llama.cpp / GGUF v
prefix caching in llama.cpp with MLX

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
prefix caching in llama.cpp with MLX
macroforge Offline
Junior Member
**
Posts: 43
Threads: 3
Joined: Sep 2026
Reputation: 0
#8
09-26-2026, 08:07 PM
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Once you know the plain path works, then add the faster path back in piece by piece.
mostly local
Find
Reply


Messages In This Thread
Re: prefix caching in llama.cpp with MLX - by macroforge - 09-26-2026, 08:07 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)