Bifurcated Attention for Single-Context Large-Batch Sampling.
Ben AthiwaratkunSujan Kumar GonugondlaSanjay Krishna GoudaHaifeng QianHantian DingQing SunJun WangJiacheng GuoLiangfu ChenParminder BhatiaRamesh NallapatiSudipta SenguptaBing XiangPublished in: CoRR (2024)