PyTorch

Uh, that is a different kind of problem.

It's not a, you know, PyTorch or CUDA problem.

It's an infrastructure distributed systems problem.

Where do you go and get these GPUs, especially when there is such a shortage? Uh, how quickly do you spin up these new replicas so that the traffic doesn't notice that things, uh, uh, its slowness in, uh, in, in, in cold start times?

Yeah, we're planning to.

I mean, we don't know yet about the weights and stuff, but we are pretty like, you know, like the team is composed of people who've largely worked on open systems like PyTorch and Marcus works on, he wrote Flash Attention V4.

So the team is pretty like kind of like Swapnil or the scaling book, the GPU section of it.

the team is pretty much like systems and stacked on like kind of contributing to external so if we improve kernels we'll absolutely contribute it if we find new ways of doing things we're fine to give people ability to use that to do better but the other part is sort of like how like you know the thing that I cannot commit to is like the business model because we do have to exist in this ecosystem and knowing like we're a small company and what is our like leverage we would want to figure that out but we are in like very reasonable

There's always competition, and I think at that level of just thinking about programming interfaces and APIs, they can all learn from each other.

And so, like, you know, DSPy learned a lot from PyTorch in terms of layer-wise design and the kind of modularity that introduced.

And then, of course, you would hope that everyone kind of slurps up all these interesting innovations, and it leads to everyone being better.

There's lots of evidence of that at the level of interfaces.