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
phasescope Offline
Junior Member
**
Posts: 41
Threads: 0
Joined: Oct 2026
Reputation: 0
#4
10-11-2026, 01:09 PM
Quote:Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Wort

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal.
Find
Reply


Messages In This Thread
prefix caching in llama.cpp - by vrambandit - 10-11-2026, 06:20 AM
Re: prefix caching in llama.cpp - by vrambandit - 10-11-2026, 08:41 AM
Re: prefix caching in llama.cpp - by vrambandit - 10-11-2026, 01:48 PM
Re: prefix caching in llama.cpp - by pixelcrate82 - 10-11-2026, 08:53 AM
Re: prefix caching in llama.cpp - by phasescope - 10-11-2026, 01:09 PM
Re: prefix caching in llama.cpp - by embershed99 - 10-12-2026, 02:08 AM
Re: prefix caching in llama.cpp - by visionyard23 - 10-12-2026, 10:33 AM
Re: prefix caching in llama.cpp - by edgequill - 10-12-2026, 10:53 AM
Re: prefix caching in llama.cpp - by phasescope - 10-13-2026, 01:54 AM
Re: prefix caching in llama.cpp - by embershed99 - 10-12-2026, 11:20 PM
Re: prefix caching in llama.cpp - by northcraft90 - 10-12-2026, 11:51 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)