Beiquan Cao

According to our database, Beiquan Cao authored at least 2 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Dispenser: Hierarchical KV Cache Management for Efficient LLM Generative Inference.

Beiquan Cao, Kaigui Bian, Guojie Luo, Joongheon Kim

Proceedings of the 31th IEEE International Conference on Parallel and Distributed Systems, 2025

2024

ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction.

Renze Chen, Zhuofeng Wang, Beiquan Cao, Tong Wu, Size Zheng, Xiuhong Li, Xuechao Wei, Shengen Yan, Meng Li, Yun Liang

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024