Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yuchen Teng

Yuchen Teng

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Distributed×1AI×1ML×1Performance×1

Frequent co-authors

Zhuoren Ye1×
Tianyu Wo1×
Dinghao Xue1×
Mingming Zhang1×
Chunming Hu1×
Renyu Yang1×

Research Timeline

2026
CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

This paper proposes CrossPool, a serving engine for cold Machine Learning Models (LLMs) that separates weights and KV-cache into two GPU memory pools to improve GPU memory utilization and long-context support.

Highlighted terms show continued research focus across papers

Papers

cs.DCcs.AIcs.LGEmpiricalRecentJun 23, 2026

CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

Zhuoren Ye, Tianyu Wo, Dinghao Xue, Mingming Zhang +3 more

This paper proposes CrossPool, a serving engine for cold Machine Learning Models (LLMs) that separates weights and KV-cache into two GPU memory pools to improve GPU memory utilization and long-context…

View →