addison(@addikala):New in @berkeley_ai blog. Cao et al. create new kernel optimizer K-search and use it to auto adapt CUDA to MLX. Their attention translation measures 0.97x speed to Apple’s native implementation. Translate your code with their OSS tool. Available now. https://t.co/SKl1ojlTOo 🐻📄

addison

@addikala

phd student @ucberkeley | blog editor @berkeley_ai

Joined February 2020

21 Following 21 Followers

addison@addikala

2026.07.30 00:26

New in @berkeley_ai blog. Cao et al. create new kernel optimizer K-search and use it to auto adapt CUDA to MLX. Their attention translation measures 0.97x speed to Apple’s native implementation. Translate your code with their OSS tool. Available now. 🐻📄