Triton - Open source neural network programming on GPUs

[igor_kavinski]

Introducing Triton: Open-source GPU programming for neural networks

We’re releasing Triton 1.0, an open-source Python-like programming language which enables researchers with no CUDA experience to write highly efficient GPU code—most of the time on par with what an expert would be able to produce.

openai.com

Hopefully CUDA dies soon?

 

[lantis3]

https://github.com/openai/triton Triton 2.0 is out.

Another AI language.

Mojo 🔥: Powerful CPU+GPU Programming

Mojo is a programming language that enables fast & portable CPU+GPU programs to execute via the MAX Platform

www.modular.com

A Python superset, claims faster than Python 35,000x

Mojoð¥ FAQ | Modular

Answers to questions we expect about Mojo.

docs.modular.com

Seems not open source yet.

GitHub - modular/max: The MAX Platform (includes Mojo)

The MAX Platform (includes Mojo). Contribute to modular/max development by creating an account on GitHub.

github.com

Never a good programmer, and I'm too old to learn new languages.