Hands-on with the Google TPUv2

gradient

#1

Over the last year or so we have seen a lot of new developments in the AI chip space. Companies like Intel, Graphcore, Cerebras, Vathys, and more have been racing to develop newer hardware architectures that promise to take the general compute model of a GPU and build it specifically for the task of training and deploying deep learning models.


This is a companion discussion topic for the original entry at https://blog.paperspace.com/the-tpu-is-weird-but-its-going-to-change-everything/

#2

We just added a new section to the Help Center covering the TPUv2. Check it out!