Hacker News new | past | comments | ask | show | jobs | submit login

Keep in mind that what you linked refers to TPUv1, which is built for quantized 8-bit inference. The TPUv2, which was announced in this blog post, is for general purpose training and uses 32-bit weights, activations, and gradients.

It will have very different performance characteristics.




Thanks for pointing that out!




Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: