1

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. …

Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, Hao Zhang

LoongServe: Efficiently Serving Long-context Large Language Models with Elastic Sequence Parallelism

The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between …

Bingyang Wu, Shengyu Liu, Yinmin Zhong, Peng Sun, Xuanzhe Liu, Xin Jin

MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs

We present the design, implementation and engineering experience in building and deploying Optimus, a production system for training …

Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, Xin Liu

AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving

Model parallelism is conventionally viewed as a method to scale a single large deep learning model beyond the memory limits of a single …

Zhuohan Li, Lianmin Zheng, Yinmin Zhong, Vincent Liu, Ying Sheng, Xin Jin, Yanping Huang, Zhifeng Chen, Hao Zhang, Joseph E. Gonzalez, Ion Stoica

ElasticFlow: An Elastic Serverless Training Platform for Distributed Deep Learning

This paper proposes ElasticFlow, an elastic serverless training platform for distributed deep learning. ElasticFlow provides a …

Diandian Gu, Yihao Zhao, Yinmin Zhong, Yifan Xiong, Zhenhua Han, Peng Cheng, Fan Yang, Gang Huang, Xin Jin, Xuanzhe Liu