Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Does anyone know if GPU passthrough is available in any kind of macOS guests? I was hoping to run fast LLM inference in containers or virt guests.


There is a paravirtualized GPU available to macOS hosts. But it’s a bit limited and might not work for LLMs but worth trying since it might work.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: