Tim Davis

It will still be a very large workload, but the number of people doing it will actually regress quite significantly.

And look, we obviously had a thesis and other people had their theses too, but that turned out to be somewhat correct.

And so what we realized was, today with PyTorch, if you build a PyTorch model, you can't actually deploy that at large scale in production.

And that's why open software today like VLM, which is an open serving framework, it got created to essentially help fix the problem that

PyTorch can't actually serve large-scale production workloads natively, right?

When we created TensorFlow, it was the other way around.

TensorFlow was wonderful at large-scale inference and not that great at, particularly from a usability standpoint, not that great at training.

PyTorch was incredibly great at training, but not that great at inference, right?

And so...

What we realized was, well, there's going to be an opportunity here to build a native framework, a new framework.

And, you know, it's open source where it starts with inference and we could do large scale inference and we can do large scale inference across compute types.

And then we can add training actually easily enough.

And the beauty of it is it has a serving component to it natively.

So you can essentially run open models, all of the popular open models that you would otherwise be aware of.

You can serve them.

So now you can actually serve these things on, you know, increasingly we actually last month announced Mac support.

So running these things locally on devices like Mac machines, but then also taking that to very large data center workloads, right?

And so at that point, what we realized was, hey, look, we have an opportunity here to really take a lot of our knowledge in AI framework design and build a new framework.

And then above that, increasingly, I will say that AI is now a full-stack challenge.

I certainly believe that