Elamur Research⌕
☰
home / authors / Xin Jin

Xin Jin

Xin Jin has 5 papers in our library, in 2023–2024, most of them on Language models & pretraining, GPU & parallel computing; often with Yinmin Zhong, Shengyu Liu, Xuanzhe Liu.

5 papers in our library · 2023–2024

OpenAlex · ORCID · Wikidata · h-index 27 · 129 works · 2,123 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 781 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #2910

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Peking UniversityBeijing · China2003–2026 · 53 papersEducation 2007–2011 · BS, Computer ScienceEmployment since 2021 · Associate Professor, Computer Sciencecurrent🎓Qingdao UniversityQingdao · China2022–2025 · 13 papers🔬State Key Laboratory of Bio-Fibers and Eco-TextilesQingdao · China2022–2025 · 11 papers🎓Qinghai UniversityXining · China2012–2025 · 4 papers🎓Southeast UniversityNanjing · China2005–2024 · 4 papers🤝National Computer Network Emergency Response Technical Team/Coordination Center of ChinarBeijing · China2018–2019 · 4 papers🎓George Washington UniversityWashington · United States2010–2012 · 4 papers🎓Sichuan UniversityChengdu · China2015–2019 · 3 papers🎓Princeton UniversityPrinceton · United States2011–2016 · 3 papersEducation 2011–2016 · PhD, Computer Science🎓Johns Hopkins UniversityBaltimore · United States2017–2020 · 2 papersEmployment 2017–2020 · Assistant Professor, Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 21 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksHardware and Architecture · 5 worksArts and Humanities · 2 worksInformation Systems · 3 worksComputer Networks and Communications · 3 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3 worksGPU & parallel computing · 1 work

 Works by year

2020s

20243 papers20232 papers

 Papers

The most cited first (OpenAlex and our library).

  1. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving (2024 · 409 citations)
    LLM inference has two phases with different profiles. Prefill processes the whole prompt in one compute-heavy step. Decoding emits one token per step and is bound by memory bandwidth. Mainstream systems batch both phases on the same GPUs. As a result, prefill delays inflate TPOT, decoding work inflates TTFT, and both…
  2. AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (2023 · 170 citations)
    AlpaServe asks how to serve many large deep learning models on a shared GPU cluster when request traffic is highly bursty.
  3. LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism (2024 · 131 citations)
    Long-context LLMs (Claude-3, Gemini-1.5 and LWM all accept up to 1M tokens) create very uneven resource demands.
  4. Fast Distributed Inference Serving for Large Language Models (2023 · 123 citations)
    FastServe, from Peking University, is a distributed serving system for large language models that targets the latency of interactive applications.
  5. FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion (2024 · 67 citations)
    Tensor parallelism splits individual layers of large models across GPUs. This lowers latency, but it adds AllGather and ReduceScatter traffic that can take a large share of runtime. Earlier overlap schemes, such as TransformerEngine, cut a GEMM and its collective into a few chunks, one per device, and schedule them…

All works

7 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

  1. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model ServingOSDI 2024Yinmin Zhong, Shengyu Liu, Junda Chen, et al.2024 · 409 citations
  2. AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning ServingOSDI 2023Zhuohan Li, Lianmin Zheng, Yinmin Zhong, et al.2023 · 170 citations
  3. LoongServe: 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 citations
  4. Fast Distributed Inference Serving for Large Language ModelsarXiv 2023Bingyang Wu, Yinmin Zhong, Zili Zhang, et al.2023 · 123 citations
  5. FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel FusionarXiv:2406.06858Li-Wen Chang, Wenlei Bao, Qi Hou, et al.2024 · 67 citations
  6. RackSched: A Microsecond-Scale Scheduler for Rack-Scale Computers (Technical Report) ↗arXiv (Cornell University) · no summary yetHang Zhu et al.2020
  7. NetChain: Scale-Free Sub-RTT Coordination (Extended Version) ↗arXiv (Cornell University) · no summary yetXin Jin et al.2018

 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 781 times (of the 149,439 papers whose bibliographies we read); 26 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xin-jin/