🧑🔬 Bingyang Wu — papers of 2024 — 1 paper, the most cited first1 paper · all years of Bingyang WuLoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence ParallelismACM SIGOPS Symposium on Operating Systems Principles (SOSP)Bingyang Wu, Shengyu Liu, Yinmin Zhong, et al.2024 · 131 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/bingyang-wu/year/2024/