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

Out of curiosity, how much more time will it cost to run this on general CPUs of users computer?


It takes a couple seconds per reply. GPUs aren't as powerful as everyone would have it, at least not for ML; you'd be lucky to get a 10x speedup.




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

Search: