Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Shangming Cai
Observed name:
Cai, Shangming
Institution:
Alibaba Group (China)
Observed institutions:
Alibaba Group (China),
Tsinghua University
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
·
280
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
·
29
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
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)
·
2
PDF
Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference
2026
·
Sun, Xun
, Chen, Shaoyuan
, et al.
·
arXiv (Cornell University)
·
1
PDF
Zswap Boost: ATC '26 Artifact
2026
·
Liu, Zheng
, Ma, Teng
, et al.
·
Zenodo (CERN European Organization for Nuclear Research)
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
Show more works
View as search
Works count:
7
Citation count:
324
H-index:
3
I10-index:
3
Year
Topic
Type
