@article{cudal2surpassingcublasperformanceformatr, title = {CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning}, author = {Songqiao Su and Xiaofei Sun and Xiaoya Li and Albert Wang and Jiwei Li and Chris Shum}, year = {2025}, eprint = {2512.02551}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.02551}, }