UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling.
Haoyu Yang, Zan Zong, Yuyang Jin, Kinman Lei, Jiaao He, Qigang Yang, Jidong Zhai
Browse the full SC paper archive.
Haoyu Yang, Zan Zong, Yuyang Jin, Kinman Lei, Jiaao He, Qigang Yang, Jidong Zhai
Browse the full SC paper archive.