Viewing profile — atairov

A technology partnership with NVIDIA to bring all the benefits of their accelerated compute platform to MAX, unifying and simplifying heterogeneous CPU+GPU development for AI devel…

I'm honoured to be the author of the first ever guest post on the Modular AI blog

I'm not that much in context regarding BLAS. People are trying to optimize the code as much as possible, but some optimizations are not approved to be merged due to over-complexity…

Hi. Thanks for commenting on this. You're correct llama2.c was built with runfast that doesn't execute on cores via OMP. This made comparison fair, since in Mojo the parallelize he…

If your goal is to make it as fast as possible, then for sure Python implementation is not a solution here. I think for this exactly reason llama.cpp got high attention

Regarding the original llama2.c as I believe the value proposition is to have simple implementation that can execute the inference locally on wide variety of platforms. What if we …

Personally for me the value was to implement a complex logic from a scientific paper in a pure Python. It helps to understand the essence of a cutting edge AI technology. And it's …

1.3 tok / sec is something similar to my Python version port performance, but I tried on M1 Max

Thanks for sharing this! It's great to have a reference implementation written on java lang. With given original simplicity it's really easy to follow llama architecture logic. Jus…