Is there any project that showcases Mojo for running neural network models on the GPU - like ideally something like llama.cpp that could run one or more existing models to showcase the readability and performance?
Is there any project that showcases Mojo for running neural network models on the GPU - like ideally something like llama.cpp that could run one or more existing models to showcase the readability and performance?
Something like this https://github.com/tairov/llama2.mojo?