Elamur Research⌕
☰
home / authors / Yinmin Zhong

Yinmin Zhong

Yinmin Zhong has 6 papers in our library, in 2023–2024, most of them on Language models & pretraining, GPU & parallel computing; often with Xin Jin, Shengyu Liu, Xuanzhe Liu.

6 papers in our library · 2023–2024

OpenAlex · ORCID · h-index 8 · 26 works · 240 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 1,379 times in our library · ⭐ Paper Stars ranking: #2609

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 · China2023–2026 · 17 paperscurrent🏢DeepSeekHangzhou · China2026 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 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 · 6 worksHardware and Architecture · 6 worksArts and Humanities · 3 worksInformation Systems · 4 worksComputer Networks and Communications · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 4 worksGPU & parallel computing · 2 works

 Works by year

2020s

20244 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. MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs (2024 · 157 citations)
    When an LLM training job takes over a whole cluster of tens of thousands of GPUs, two engineering problems dominate.
  4. 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.
  5. 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.
  6. 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…

 Co-authors here

12 of 19 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 1,379 times (of the 149,439 papers whose bibliographies we read); 171 citing papers with a page here →.

Updated

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