cuda-l2-kernel-optimization

【效率与协作】Uses LLMs with RL to automatically optimize HGEMM CUDA kernels across 1,000 configurations, systematically outperforming NVIDIA's cuBLAS and cuBLASLt through continued pretraining, general RL, and specialized HGEMM RL stages.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准