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
kernelrunner Offline
Junior Member
**
Posts: 41
Threads: 7
Joined: Sep 2026
Reputation: 0
#5
10-18-2026, 06:23 PM
Quote:A couple questions before I guess too hard. What model, what runtime, and roughly what context size?

I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
small models can still be good
Find
Reply


Messages In This Thread
prefix caching in llama.cpp - by vectorport - 10-17-2026, 02:04 PM
Re: prefix caching in llama.cpp - by embershed99 - 10-18-2026, 02:04 PM
Re: prefix caching in llama.cpp - by embershed99 - 10-18-2026, 07:39 PM
Re: prefix caching in llama.cpp - by bytesupply76 - 10-19-2026, 01:18 AM
Re: prefix caching in llama.cpp - by vrambandit - 10-18-2026, 05:41 PM
Re: prefix caching in llama.cpp - by kernelrunner - 10-18-2026, 06:23 PM
Re: prefix caching in llama.cpp - by thetagrid15 - 10-18-2026, 11:07 PM
Re: prefix caching in llama.cpp - by northgrid33 - 10-19-2026, 12:43 AM
Re: prefix caching in llama.cpp - by northcraft90 - 10-19-2026, 01:32 AM
Re: prefix caching in llama.cpp - by vrambandit - 10-19-2026, 02:26 AM
Re: prefix caching in llama.cpp - by mellowwire98 - 10-19-2026, 03:18 AM
Re: prefix caching in llama.cpp - by latentcraft - 10-19-2026, 04:03 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)