Get started
Author

Shangming Cai

Observed name: Cai, Shangming
ORCID: 0000-0002-0902-7774
Observed ORCID: 0000-0002-0902-7774
OpenAlex ID: A5036856464
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
2025 · Ruoyu Qin, Zheming Li, et al. · ACM Transactions on Storage · 34
PDF
CRaft: An Erasure-coding-supported Version of Raft for Reducing Storage Cost and Network Cost
2020 · Zizhong Wang, Tongliang Li, et al. · File and Storage Technologies · 27
DynaComm: Accelerating Distributed CNN Training Between Edges and Clouds Through Dynamic Communication Scheduling
2021 · Shangming Cai, Dongsheng Wang, et al. · IEEE Journal on Selected Areas in Communications · 12
PDF
Zswap Boost: ATC '26 Artifact
2026 · Liu, Zheng, Ma, Teng, et al. · Zenodo (CERN European Organization for Nuclear Research)
Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference
2026 · Sun, Xun, Chen, Shaoyuan, et al. · arXiv (Cornell University)
PDF
TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM Serving
2026 · Ren, Feng, Qin, Ruoyu, et al. · arXiv (Cornell University)
PDF
CARD: A Congestion-Aware Request Dispatching Scheme for Replicated Metadata Server Cluster
2020 · Shangming Cai, Dongsheng Wang, et al. · Proceedings of the International Conference on Parallel Processing
Works count: 7
Citation count: 73
H-index: 3
I10-index: 3
Year
Topic
Type