alt Hacker NewsMostly working on my personal project, pi-container[0], for running the pi coding agent in an isolated and more secure container environment.
Mostly working on my personal project, pi-container[0], for running the pi coding agent in an isolated and more secure container environment.
I've been doing the same, just with a llama-cpp local serve integrated + tor as a proxy. I was wondering whether there's a way to limit the heating issue with macbooks when running local model: do you think that limiting the number of cpu in the container is enough (albeit slowing down the llama-cpp inference speed) or is there a better way?