What 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!

▲

Archit3ch 5 hours ago | parent | next [-]

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.

▲

Pragmata 6 hours ago | parent | prev [-]

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

	▲	vforno 6 hours ago \| parent [-]
		We're working on it right now with a pull request that will also arrive for opencode!