Dapeng Nie

According to our database, Dapeng Nie authored at least 4 papers between 2023 and 2026.

Collaborative distances:

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

2026

HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds.

Chiheng Lou, Sheng Qi, Chao Jin, Dapeng Nie, Haoran Yang, Yu Ding, Xuanzhe Liu, Xin Jin

Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, 2026

2025

Towards Swift Serverless LLM Cold Starts with ParaServe.

Chiheng Lou, Sheng Qi, Chao Jin, Dapeng Nie, Haoran Yang, Xuanzhe Liu, Xin Jin

CoRR, February, 2025

Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference.

Minchen Yu, Ao Wang, Dong Chen, Haoxuan Yu, Xiaonan Luo, Zhuohao Li, Wei Wang, Ruichuan Chen, Dapeng Nie, Haoran Yang, Yu Ding

Proceedings of the 2025 USENIX Annual Technical Conference, 2025

2023

FaaSwap: SLO-Aware, GPU-Efficient Serverless Inference via Model Swapping.

Minchen Yu, Ao Wang, Dong Chen, Haoxuan Yu, Xiaonan Luo, Zhuohao Li, Wei Wang, Ruichuan Chen, Dapeng Nie, Haoran Yang

CoRR, 2023