EL-Attention: Memory Efficient Lossless Attention for Generation.
Yu Yan, Jiusheng Chen, Weizhen Qi, Nikhil Bhendawade, Yeyun Gong, Nan Duan, Ruofei Zhang
Browse the full ICML paper archive.
Yu Yan, Jiusheng Chen, Weizhen Qi, Nikhil Bhendawade, Yeyun Gong, Nan Duan, Ruofei Zhang
Browse the full ICML paper archive.