1 citations · 1 across the 1 of their papers we have counts for
3 papers
cs.CL2024
Expert-Token Resonance MoE: Bidirectional Routing with Efficiency Affinity-Driven Active Selection
Jing Li, Zhijie Sun, Dachao Lin +5
Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer fr…
cs.DC2024★ 1 cited
WindGP: Efficient Graph Partitioning on Heterogenous Machines
Li Zeng, Haohan Huang, Binfan Zheng +6
Graph Partitioning is widely used in many real-world applications such as fraud detection and social network analysis, in order to enable the distributed graph computing on large g…
cs.LG2024
LocMoE: A Low-Overhead MoE for Large Language Model Training
Jing Li, Zhijie Sun, Xuan He +6
The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and…