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

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
prefix caching in llama.cpp
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#5
09-11-2026, 12:53 PM
I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
prefix caching in llama.cpp - by bytesupply76 - 09-07-2026, 03:04 PM
Re: prefix caching in llama.cpp - by vrambandit - 09-07-2026, 11:46 PM
Re: prefix caching in llama.cpp - by embershed99 - 09-10-2026, 11:51 PM
Re: prefix caching in llama.cpp - by thetagrid15 - 09-11-2026, 12:09 PM
Re: prefix caching in llama.cpp - by vrambandit - 09-11-2026, 12:53 PM
Re: prefix caching in llama.cpp - by phasescope - 09-11-2026, 03:24 PM
Re: prefix caching in llama.cpp - by pixelcrate82 - 09-11-2026, 11:44 PM
Re: prefix caching in llama.cpp - by visionyard23 - 09-12-2026, 08:34 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)