10-14-2026, 09:21 PM
I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
|
prefix caching in llama.cpp
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
prefix caching in llama.cpp - by mellowwire98 - 10-14-2026, 07:37 PM
Re: prefix caching in llama.cpp - by thetagrid15 - 10-14-2026, 09:21 PM
|