alt Hacker NewsWhat causes problems is the rewriting in this case are only read while writing is the cache! However, I'm working to improve more and more and make some parts lighter!
Replies
Pragmata • yesterday at 9:48 PM
Is it possible to run this into an agent? pi, claude code, etc..? I've only tried it with LM studio, but i'm guessing this is a bit different
➕ show 1 reply
You can keep the KV cache in (possibly Unified) RAM to avoid SSD writes entirely. Not sure if it would fit on a 32GB laptop, though.