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

I thought they use GPU for learning and TPU for inference, I’m open to been corrected.


The first tpu they made was inference only. Everything since has been used for training. I think that means they weren't using it for training in 2015 but rather 2017 based on Wikipedia.


The first TPU they *announced" was for inference


Some details here: https://news.ycombinator.com/item?id=42392310


no. for internal training most work is done on TPUs, which have been explicitly designed for high performance training.


I've heard its a mixture because they can't source enough in-house compute




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

Search: