ctrl icon indicating copy to clipboard operation
ctrl copied to clipboard

Published 20 hours ago • verified publisher icon salesforce

Running the model on TPUs?

Open vessenes opened this issue 5 years ago • 2 comments

Hi,

I have the 256 and 512 models working on GCP with a Tesla V100. Text generates, but slowly, and I'm wanting to get faster generation out of the system. I thought running CTRL on TPUs could get me faster text, but I have no idea how to do that.

Do you have an incantation or pointer that would let me point CTRL at a TPU?

vessenes avatar Oct 25 '19 23:10 vessenes

Second this!

dimitri320 avatar Oct 26 '19 07:10 dimitri320

I haven't quite figured out how to get TPUs to be faster than GPUs for inference. I'll probably look into this soon. It's especially more complicated with top-k/nucleus sampling and other add-ons. Seems like others have found the same behavior.

keskarnitish avatar Oct 28 '19 17:10 keskarnitish