Jian Lin

Jian Lin

Auto-generated profile, based on publicly available information

Jian Lin

Hong Kong University of Science and Technology, Hong Kong, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
22 April 2024
Verified
Conference Paper
Open access
ZHZicong Hong
Zicong Hong
JLJian Lin
Jian Lin
SGSong Guo
Song Guo
SLSifu Luo
Sifu Luo
WCWuhui Chen
Wuhui Chen
YYYue Yu
Yue Yu


1 January 2020 in Journal of Inorganic Materials
Verified
Journal Article
Open access
PDF file
CYChang Yuchen
Chang Yuchen
LZLin Ziyang
Lin Ziyang
XXXie Xin
Xie Xin
WZWu Zhangfan
Wu Zhangfan
YAYao Aihua
Yao Aihua
CXCui Xu
Cui Xu

18 May 2026 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
JLJian Lin
Jian Lin
JMJiazhi Mi
Jiazhi Mi
ZHZicong Hong
Zicong Hong
HWHaodong Wang
Haodong Wang
QLQianli Liu
Qianli Liu
SGSong Guo
Song Guo
Supporting long-context LLMs is challenging due to the substantial memory demands of the key–value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this strategy quickly hits a ceiling: sparsity cannot be pushed further without degrading accuracy. As a result, when context length and batch size grow, the volume of KV transfers rises sharply and becomes the dominant source of decoding latency. We present KVD rive, a holistic multi-tier KV cache management system spanning GPU memory, host DRAM, and SSD. Unlike prior work that pursues greater sparsity through algorithmic refinements, KVD rive tackles the problem from a systems perspective—jointly orchestrating cache placement, pipeline scheduling, and cross-tier coordination to sustain high-throughput inference under tight GPU budgets. KVD rive advances three fundamental capabilities: it adapts cache management to attention behavior to maximize reuse and minimize redundant data movement; it restructures the decoding pipeline to overlap I/O- and CPU/GPU compute-bound stages, eliminating stalls across heterogeneous resources; and it harmonizes data movement across memory tiers to unlock scalable long-context inference far beyond GPU and DRAM limits. We have implemented a fully functional prototype of KVD rive and evaluated it on long-context benchmarks with popular LLMs. The system achieves up to 1.74× higher throughput compared to state-of-the-art works while preserving accuracy.