Since Chris is lurking: will Mojo on GPUs be more like using Jax (relying on compiler), Triton (more control, but abstracted), or more like CUDA (close to maximal control)? Combination? Nvidia and AMD support out of box?
Modular is enabling all of the above for different audiences. MAX provides an operator-graph level abstraction like PyTorch or JAX have, and we expect a bunch of high level libraries like nn.module to get built out over time by the community. You can also go directly to the GPU with a classical CUDA-like programming model for maximal control.
In between we have something we're cooking that I think will be pretty interesting for GPU kernel authors, but it isn't public yet. :-)
The nice thing about this is that it is one system that scales, instead of a bunch of different/inconsistent tech built by different teams over many years, held together with duct tape. Simple and consistent makes it much easier to do the kinds of research and experimentation that power AI ecosystem.
In between we have something we're cooking that I think will be pretty interesting for GPU kernel authors, but it isn't public yet. :-)
The nice thing about this is that it is one system that scales, instead of a bunch of different/inconsistent tech built by different teams over many years, held together with duct tape. Simple and consistent makes it much easier to do the kinds of research and experimentation that power AI ecosystem.