Zeyu Li

Zeyu Li

Auto-generated profile, based on publicly available information

Zeyu Li

The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2023 in The Journal of Chemical Physics
Verified
Journal Article
Open access
PDF file
JZJinzhe Zeng
Jinzhe Zeng
DZDuo Zhang
Duo Zhang
DLDenghui Lu
Denghui Lu
PMPinghui Mo
Pinghui Mo
ZLZeyu Li
Zeyu Li
HWHan Wang
Han Wang
DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used in the fields of physics, chemistry, biology, and material science for studying atomistic systems. The current version of DeePMD-kit offers numerous advanced features, such as DeepPot-SE, attention-based and hybrid descriptors, the ability to fit tensile properties, type embedding, model deviation, DP-range correction, DP long range, graphics processing unit support for customized operators, model compression, non-von Neumann molecular dynamics, and improved usability, including documentation, compiled binary packages, graphical user interfaces, and application programming interfaces. This article presents an overview of the current major version of the DeePMD-kit package, highlighting its features and technical details. Additionally, this article presents a comprehensive procedure for conducting molecular dynamics as a representative application, benchmarks the accuracy and efficiency of different models, and discusses ongoing developments.

3 August 2025
Verified
Conference Paper
Open access
YWYuxin Wang
Yuxin Wang
YCYuhan Chen
Yuhan Chen
ZLZeyu Li
Zeyu Li
XKXueze Kang
Xueze Kang
YFYuchu Fang
Yuchu Fang
XCXiaowen Chu
Xiaowen Chu

30 March 2025
Verified
Conference Paper
Open access
RFRuibo Fan
Ruibo Fan
XYXiangrui Yu
Xiangrui Yu
PDPeijie Dong
Peijie Dong
ZLZeyu Li
Zeyu Li
GGGu Gong
Gu Gong
XCXiaowen Chu
Xiaowen Chu

5 October 2026 in ACM Transactions on Computer Systems
Verified
Journal Article
Open access
WLWeile Luo
Weile Luo
RFRuibo Fan
Ruibo Fan
ZLZeyu Li
Zeyu Li
DDDayou Du
Dayou Du
HLHongyuan Liu
Hongyuan Liu
XCXiaowen Chu
Xiaowen Chu
This study presents a comprehensive multi-level analysis of the NVIDIA Hopper GPU architecture, focusing on its performance characteristics and novel features. We benchmark Hopper’s memory subsystem, highlighting improvements in the L2 partitioned cache and global memory access compared to Ampere and Ada Lovelace. The evaluation of Hopper’s fourth-generation tensor cores reveals the benefits of FP8 precision and asynchronous wgmma instructions for matrix operations. Additionally, we investigate the performance of DPX instructions for dynamic programming, distributed shared memory (DSM) for inter-SM communication, and the Tensor Memory Accelerator (TMA) for asynchronous data movement. Through multi-level evaluation, we discover that the Hopper architecture demonstrates significant acceleration potential in real-world applications. For instance, the asynchronous programming model supported by TMA achieves a 1.5× speedup in matrix multiplication, FP8 delivers nearly double the performance of FP16, and DPX instructions accelerate a computational biology algorithm by at least 4.75×. Our findings provide actionable insights for optimizing compute-intensive workloads, from AI training to bioinformatics, on Hopper GPUs.

22 March 2026
Verified
Conference Paper
Open access
RFRuibo Fan
Ruibo Fan
XYXiangrui Yu
Xiangrui Yu
XPXinglin Pan
Xinglin Pan
ZLZeyu Li
Zeyu Li
WLWeile Luo
Weile Luo
XCXiaowen Chu
Xiaowen Chu
Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference slowdowns due to fundamental design mismatches with GPU architectures: at the kernel level, variable-length bitstreams produced by traditional entropy codecs break SIMT parallelism; at the system level, decoupled pipelines lead to redundant memory traffic. We present ZipServ, a lossless compression framework co-designed for efficient LLM inference. ZipServ introduces Tensor-Core-Aware Triple Bitmap Encoding (TCA-TBE), a novel fixed-length format that enables constant-time, parallel decoding, together with a fused decompression-GEMM (ZipGEMM) kernel that decompresses weights on-the-fly directly into Tensor Core registers. This '' load-compressed, compute-decompressed '' design eliminates intermediate buffers and maximizes compute intensity. Experiments show that ZipServ reduces the model size by up to 30%, achieves up to 2.21× kernel-level speedup over NVIDIA's cuBLAS, and expedites end-to-end inference by an average of 1.22× over vLLM. ZipServ is the first lossless compression system that provides both storage savings and substantial acceleration for LLM inference on GPUs.

5 July 2026
Verified
Conference Paper
Open access
XYXiangrui Yu
Xiangrui Yu
RFRuibo Fan
Ruibo Fan
ZLZeyu Li
Zeyu Li
WLWeile Luo
Weile Luo
GGGu Gong
Gu Gong
XCXiaowen Chu
Xiaowen Chu