Neuromorphic spike-based large language model

This work proposes a unified neuromorphic spike-based large-language-model (NSLLM) framework to simultaneously address the challenges of high energy consumption and low interpretability in LLMs. Our framework transforms LLMs into efficient NSLLMs by converting their behaviors into neural dynamics-such as spike trains-through rigorous mathematical modeling and complemented by advanced techniques including quantization and sparsification. This transformation also enables the analysis of information encoding processes using computational neuroscience tools, thereby offering a novel neuroscientific perspective that conceptualizes LLMs as neural populations to enhance their interpretability. Leveraging a hardware-algorithm co-design paradigm, an NSLLM can completely eliminate matrix multiplication (MatMul) while maintaining high performance. We designed a custom MatMul-free hardware core on the VCK190 field-programmable gate array to validate the 1.5-billion-parameter NSLLM, achieving a dynamic power consumption of only 13.849 W and an inference throughput of 161.8 tokens per second. Compared with the A800 GPU, this implementation improves energy efficiency, memory usage and inference throughput by 19.8[Formula: see text], 21.3[Formula: see text] and 2.2[Formula: see text], respectively. This work provides a novel perspective within a unified framework to enhance both the energy efficiency and interpretability of LLMs, offering valuable insights for future neuromorphic chip designs tailored for large models.

Authors

Institutions

Publication Details

Journal
National Science Review
Published
2025-12-03
DOI
https://doi.org/10.1093/nsr/nwaf551
Citations
1
Primary Topic
Advanced Memory and Neural Computing
Type
article
Field-Weighted Citation Impact
0.73

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Neuromorphic spike-based large language model

Peng Zhou, Jiangbo Qian, Xuerui Qiu, Shaowei Gu et al.
1 citations
National Science Review
Advanced Memory and Neural Computing
0.73
article

Neuromorphic spike-based large language model

Peng Zhou, Jiangbo Qian, Xuerui Qiu, Shaowei Gu, Ruijie Zhu, Yonghong Tian, Man Yao, Tiejun Huang, Yang Tian, Jason K. Eshraghian, Mohammed Elbtity, Лей Ма, Jiahong Zhang, Xu Han, Yuqi Pan, Yunhui Xu, Bo Xu, Yuhong Chou, Qinghao Wen
article en
1 citations

Abstract

This work proposes a unified neuromorphic spike-based large-language-model (NSLLM) framework to simultaneously address the challenges of high energy consumption and low interpretability in LLMs. Our framework transforms LLMs into efficient NSLLMs by converting their behaviors into neural dynamics-such as spike trains-through rigorous mathematical modeling and complemented by advanced techniques including quantization and sparsification. This transformation also enables the analysis of information encoding processes using computational neuroscience tools, thereby offering a novel neuroscientific perspective that conceptualizes LLMs as neural populations to enhance their interpretability. Leveraging a hardware-algorithm co-design paradigm, an NSLLM can completely eliminate matrix multiplication (MatMul) while maintaining high performance. We designed a custom MatMul-free hardware core on the VCK190 field-programmable gate array to validate the 1.5-billion-parameter NSLLM, achieving a dynamic power consumption of only 13.849 W and an inference throughput of 161.8 tokens per second. Compared with the A800 GPU, this implementation improves energy efficiency, memory usage and inference throughput by 19.8[Formula: see text], 21.3[Formula: see text] and 2.2[Formula: see text], respectively. This work provides a novel perspective within a unified framework to enhance both the energy efficiency and interpretability of LLMs, offering valuable insights for future neuromorphic chip designs tailored for large models.

National Science ReviewVol. 13(4)
Ningbo University (CN), University of Technology Sydney (AU), The University of Sydney (AU), Hong Kong Polytechnic University (HK), University of California, Santa Cruz (US), Chinese Academy of Sciences (CN), Peking University (CN), Beijing Academy of Social Sciences (CN), Center for Excellence in Brain Science and Intelligence Technology (CN), Beijing Academy of Artificial Intelligence (CN), Advanced Micro Devices (United States) (US), Lux Research (United States) (US), Institute of Refrigeration (GB), Shanghai Jian Qiao University (CN), Shanghai Center for Brain Science and Brain-Inspired Technology (CN), University of Chinese Academy of Sciences (CN), City University of Macau (MO), Tsinghua University (CN)
National Natural Science Foundation of China, China Postdoctoral Science Foundation
Openalex Percentile: Top 21%
Advanced Memory and Neural Computing
0.73
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.