Fwiw this is what Soumith has said: "Internally at Facebook, we have a unified strategy. We say PyTorch is used for all of research and Caffe 2 is used for all of production."

https://www.oreilly.com/ideas/why-ai-and-machine-learning-re...

Its not exactly a secret that PyTorch's tradeoffs favor research and not production.

There was a great podcast with Soumith Chintala on the O'Reilly data show a couple of days back with more info on PyTorch and how it differs from Theano and Tensorflow:

https://www.oreilly.com/ideas/why-ai-and-machine-learning-re...