HPipe: Large Language Model Pipeline Parallelism for Long Context on Heterogeneous Cost-effective Devices.
Ruilong Ma, Xiang Yang, Jingyu Wang, Qi Qi, Haifeng Sun, Jing Wang, Zirui Zhuang, Jianxin Liao
Browse the full NAACL paper archive.
Ruilong Ma, Xiang Yang, Jingyu Wang, Qi Qi, Haifeng Sun, Jing Wang, Zirui Zhuang, Jianxin Liao
Browse the full NAACL paper archive.