2 papers
cs.DC2025
Themis: Efficient Sparse Model Training Through Fully Sharded Sparse Data Parallelism
Yuhao Qing, Guichao Zhu, Lintian Lei +9
Mixture-of-Experts (MoE) scales large language models cost-effectively, but expert-parallel training suffers severe straggler effects from skewed expert loads. Current systems freq…
cs.DC2018
Efficient and DoS-resistant Consensus for Permissioned Blockchains
Xusheng Chen, Shixiong Zhao, Ji Qi +10
Existing permissioned blockchain systems designate a fixed and explicit group of committee nodes to run a consensus protocol that confirms the same sequence of blocks among all nod…