Comment Comment by kolinko It originally started as a fork to Recmo’s cria pure numpy llama impl :)https://github.com/recmo/criaTook a whole night to compute a few tokens, but I used it to do the first tests.Also, my friend pasted the paper to claude and it produced a working basic impl instantly :DBut in all seriousness - I think MLX implementation would be doable, or a wrapper to the Metal gou functionality parent kolinko 2 years ago
https://github.com/recmo/cria
Took a whole night to compute a few tokens, but I used it to do the first tests.
Also, my friend pasted the paper to claude and it produced a working basic impl instantly :D
But in all seriousness - I think MLX implementation would be doable, or a wrapper to the Metal gou functionality