Jinquan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jinquan Wang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Limin Xiao
Beihang University
5 shared publications - Xiaojian Liao
Beihang University
4 shared publications - Liang Wang
Beihang University
3 shared publications - Xilong Xie
Beihang University
3 shared publications - Zhisheng Huo
Beihang University
3 shared publications - Jiashun Suo
Beihang University
2 shared publications
Latest Publications
- 5 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (2) , 597-611
Accelerating LLM Inference via Low-Bit Fine-Grained Quantization Algorithm and Bit-Level Accelerator Co-Design
Large language models (LLMs) have emerged as one of the most impactful and transformative paradigms in natural language processing. Despite their remarkable success, the intensive computational demands and substantial memory footprint impose a significant barrier to efficient LLM inference. In this paper, we present a comprehensive solution to improve LLM inference performance under ultra-low weight precision, meticulously optimized through algorithm and architecture co-design. To achieve this, we first propose a fine-grained intra-cluster bit allocation method that partitions the weights into small clusters and explicitly considers the distribution of outliers and salient points within each cluster. Then, an intra-cluster protection mechanism is proposed to selectively preserve important weights during quantization, where an extended integer format and group-wise scale factor search are further introduced to mitigate accuracy degradation caused by aggressive bit-width reduction. Furthermore, we develop a memory-aligned encoding scheme to facilitate efficient memory access while enabling flexible identification of mixed-precision representations. Finally, we design a lightweight bit-level accelerator for low-bit LLM inference, offering simplified hardware design and enhanced adaptability through parallel bit-level computation. Compared to existing state-of-the-art quantization algorithms, our algorithm achieves higher model accuracy under ultra-low weight precision. Meanwhile, the proposed bit-level accelerator delivers speedups of 1.59$\boldsymbol{\times}$ , 1.38$\boldsymbol{\times}$ , and 1.61$\boldsymbol{\times}$ , along with energy efficiency improvements of 1.52$\boldsymbol{\times}$ , 1.42$\boldsymbol{\times}$ , and 1.22$\boldsymbol{\times}$ over ANT, OliVe, and FineQ, respectively.- 5 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (2) , 597-611
Accelerating LLM Inference via Low-Bit Fine-Grained Quantization Algorithm and Bit-Level Accelerator Co-Design
Large language models (LLMs) have emerged as one of the most impactful and transformative paradigms in natural language processing. Despite their remarkable success, the intensive computational demands and substantial memory footprint impose a significant barrier to efficient LLM inference. In this paper, we present a comprehensive solution to improve LLM inference performance under ultra-low weight precision, meticulously optimized through algorithm and architecture co-design. To achieve this, we first propose a fine-grained intra-cluster bit allocation method that partitions the weights into small clusters and explicitly considers the distribution of outliers and salient points within each cluster. Then, an intra-cluster protection mechanism is proposed to selectively preserve important weights during quantization, where an extended integer format and group-wise scale factor search are further introduced to mitigate accuracy degradation caused by aggressive bit-width reduction. Furthermore, we develop a memory-aligned encoding scheme to facilitate efficient memory access while enabling flexible identification of mixed-precision representations. Finally, we design a lightweight bit-level accelerator for low-bit LLM inference, offering simplified hardware design and enhanced adaptability through parallel bit-level computation. Compared to existing state-of-the-art quantization algorithms, our algorithm achieves higher model accuracy under ultra-low weight precision. Meanwhile, the proposed bit-level accelerator delivers speedups of 1.59$\boldsymbol{\times}$ , 1.38$\boldsymbol{\times}$ , and 1.61$\boldsymbol{\times}$ , along with energy efficiency improvements of 1.52$\boldsymbol{\times}$ , 1.42$\boldsymbol{\times}$ , and 1.22$\boldsymbol{\times}$ over ANT, OliVe, and FineQ, respectively.- Open Access
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 854-868
Amove: Accelerating LLMs through Mitigating Outliers and Salient Points via Fine-Grained Grouped Vectorized Data Type
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 854-868
Open AccessAmove: Accelerating LLMs through Mitigating Outliers and Salient Points via Fine-Grained Grouped Vectorized Data Type
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 178-191
CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 178-191
Open AccessCoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory
- 16 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (4) , 1138-1151
Hierarchical Hashing: A Dynamic Hashing Method With Low Write Amplification and High Performance for Non-Volatile Memory
The hashing method is widely used as the index structure, which can be stored in NVM to improve the application performance. However, existing hashing methods may cause high extra write amplification to NVM and bring high additional storage overhead on NVM while providing low request performance. To solve these problems, we have proposed a dynamic hashing method called Hierarchical Hashing, whose basic idea is to leverage a novel hash collision resolution mechanism that can dynamically expand the size of the hash table. Hierarchical Hashing can incur no extra write amplification to NVM when resolving hash collisions. Additionally, it can directly address all cells when resizing the hash table, thereby avoiding the additional storage overhead caused by non-addressable linked lists. Furthermore, the request performance can be improved as all cells of the hash table are addressable when resizing to resolve hash collisions. The experimental results demonstrate that Hierarchical Hashing brings no extra write amplification to NVM and achieves nearly 90% space utilization and high request performance while providing 99% memory utilization, compared with existing representative hashing methods.
- 16 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (4) , 1138-1151
Hierarchical Hashing: A Dynamic Hashing Method With Low Write Amplification and High Performance for Non-Volatile Memory
The hashing method is widely used as the index structure, which can be stored in NVM to improve the application performance. However, existing hashing methods may cause high extra write amplification to NVM and bring high additional storage overhead on NVM while providing low request performance. To solve these problems, we have proposed a dynamic hashing method called Hierarchical Hashing, whose basic idea is to leverage a novel hash collision resolution mechanism that can dynamically expand the size of the hash table. Hierarchical Hashing can incur no extra write amplification to NVM when resolving hash collisions. Additionally, it can directly address all cells when resizing the hash table, thereby avoiding the additional storage overhead caused by non-addressable linked lists. Furthermore, the request performance can be improved as all cells of the hash table are addressable when resizing to resolve hash collisions. The experimental results demonstrate that Hierarchical Hashing brings no extra write amplification to NVM and achieves nearly 90% space utilization and high request performance while providing 99% memory utilization, compared with existing representative hashing methods.
- 29 March 2023
- Published by Springer Nature
- p. 722-732
Semi-supervised Person Re-identification Method Based on Voting Algorithm
- 29 March 2023
- Published by Springer Nature
- p. 722-732
Semi-supervised Person Re-identification Method Based on Voting Algorithm