AI RESEARCH

MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU

arXiv CS.LG

ArXi:2606.04847v1 Announce Type: cross Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code. Existing Large Language Models (LLMs) struggle with this task, while execution-based reinforcement learning suffers from sparse rewards, reward hacking, and