Elamur Research⌕
☰
home / authors / Zihao Ye

Zihao Ye

Zihao Ye has 5 papers in our library, in 2023–2025, most of them on Language models & pretraining, Efficient models & compression; often with Arvind Krishnamurthy, Lequn Chen, Baris Kasikci.

5 papers in our library · 2023–2025

OpenAlex · ORCID · Wikidata · h-index 17 · 57 works · 2,033 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 574 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #3977

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

🎓Fujian Agriculture and Forestry UniversityFuzhou · China2023–2026 · 5 paperscurrent🎓Zhejiang A & F UniversityLin’an Shi · China2022–2026 · 3 paperscurrent🎓Yantai UniversityYantai · China2026 · 1 papercurrent🎓University of WashingtonSeattle · United States2021–2025 · 6 papersEducation 2021–2025 · PhD student, Paul G. Allen School of Computer Science & EngineeringEmployment since 2021 · Research Assistant, Paul G. Allen School of Computer Science & Engineering🎓Hainan Normal UniversityHaikou · China2020–2024 · 6 papers🏛️Chinese Academy of SciencesBeijing · China2021–2025 · 3 papers🎓University of Chinese Academy of SciencesBeijing · China2021–2025 · 3 papers🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2019–2020 · 3 papers🎓Shenzhen UniversityShenzhen · China2023–2025 · 2 papers🎓South China Agricultural UniversityGuangzhou · China2023–2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 16 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 10The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksArts and Humanities · 4 worksArtificial Intelligence · 4 worksLanguage and Linguistics · 4 worksHardware and Architecture · 3 worksComputer Vision and Pattern Recognition · 2 worksEngineering · 1 workComputational Theory and Mathematics · 1 workElectrical and Electronic Engineering · 1 workInformation Systems · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 4 worksEfficient models & compression · 1 work

 Works by year

2020s

20251 paper20242 papers20232 papers

 Papers

The most cited first (OpenAlex and our library).

  1. FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving (2025 · 177 citations)
    FlashInfer is an attention engine for LLM inference serving. It targets two problems: serving workloads keep changing, and attention variants and GPU architectures differ widely. Today each serving system ships its own narrow attention kernels, which is costly to maintain. FlashInfer replaces them with one…
  2. Atom: Low-bit Quantization for Efficient and Accurate LLM Serving (2023 · 156 citations)
    LLM serving relies on batching to keep GPUs busy, and quantization can further reduce memory use and compute cost.
  3. Punica: Multi-Tenant LoRA Serving (2023 · 81 citations)
    Organisations that fine-tune one base LLM with LoRA for many tenants usually end up running each adapter as a separate model.
  4. NanoFlow: Towards Optimal Large Language Model Serving Throughput (2024 · 80 citations)
    LLM serving is usually assumed to be limited by memory bandwidth, because every generated token requires reading the model weights and the KV-cache.
  5. MagicPIG: LSH Sampling for Efficient LLM Generation (2024 · 68 citations)
    Serving long-context LLMs is constrained by the KV cache. It consumes GPU memory and makes decoding memory-bound. Many speedups keep only the highest-scoring keys (TopK attention). The authors show this is a biased estimator that breaks down when attention is spread out, as in aggregation tasks like common- or…

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. FlashInfer: Efficient and Customizable Attention Engine for LLM Inference ServingMLSys 2025Zihao Ye, Lequn Chen, Ruihang Lai, et al.2025 · 177 citations
  2. Atom: Low-bit Quantization for Efficient and Accurate LLM ServingMLSys 2024Yilong Zhao, Chien-Yu Lin, Kan Zhu, et al.2023 · 156 citations
  3. TensorIR: An Abstraction for Automatic Tensorized Program Optimization ↗ASPLOS 2023 · no summary yetSiyuan Feng et al.2022 · 130 citations
  4. DGL-KE ↗International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · no summary yetDa Zheng et al.2020 · 128 citations
  5. Punica: Multi-Tenant LoRA ServingMLSys 2024Lequn Chen, Zihao Ye, Yongji Wu, et al.2023 · 81 citations
  6. NanoFlow: Towards Optimal Large Language Model Serving ThroughputOSDI 2025Kan Zhu, Yufei Gao, Yilong Zhao, et al.2024 · 80 citations
  7. MagicPIG: LSH Sampling for Efficient LLM GenerationarXiv:2410.16179Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, et al.2024 · 68 citations

 Co-authors here

12 of 15 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 574 times (of the 149,439 papers whose bibliographies we read); 39 citing papers with a page here →.

Updated

↑ back to top

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