CachyLLama’s: llama.cpp fork with persistent KV cache that makes long local-agent sessions much less painful

I’m not affiliated with this project, but I’ve been running it recently and I’m surprised it hasn’t received more attention here: https://github.com/fewtarius/CachyLLama CachyLLama is a fork of llama.cpp focused on a problem that matters a lot on slower hardware: repeated prompt processing. Not only

中文全文翻译正在补齐，可先查看下方英文原文。

I’m not affiliated with this project, but I’ve been running it recently and I’m surprised it hasn’t received more attention here: https://github.com/fewtarius/CachyLLama CachyLLama is a fork of llama.cpp focused on a problem that matters a lot on slower hardware: repeated prompt processing. Not only