SLA2: Sparse-Linear Attention with Learnable Routing and QAT
arXiv:2602.12675v1 Announce Type: new Abstract: Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. …
Jintao Zhang, Haoxu Wang, Kai Jiang, Kaiwen Zheng, Youhe Jiang, Ion Stoica, Jianfei Chen, Jun Zhu, Joseph E. Gonzalez
조회수 33회