ParaDySe: A Parallel Strategy Switching Framework for Dynamic Sequences in Transformer-based Large Language Models.
Zhixin Ou, Peng Liang, Linbo Qiao, Jianchen Han, Baihui Liu
Browse the full AAAI paper archive.
Zhixin Ou, Peng Liang, Linbo Qiao, Jianchen Han, Baihui Liu
Browse the full AAAI paper archive.