>None of that is specialized to run only transformers at this point isn't this w... | Hacker News

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

		Mehvix 58 days ago \| parent \| context \| favorite \| on: 'Attention is all you need' coauthor says he's 'si... >None of that is specialized to run only transformers at this point isn't this what [etched](https://www.etched.com/) is doing?

imtringued 58 days ago [–]

Only being able to run transformers is a silly concept, because attention consists of two matrix multiplications, which are the standard operation in feed forward and convolutional layers. Basically, you get transformers for free.

kadushka 58 days ago | [–]

devil is in the details

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