5 papers
DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
Chenyang Song, Weilin Zhao, Xu Han +3
While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates significant storage and memory-acc…
Cost-Optimal Grouped-Query Attention for Long-Context Modeling
Yingfa Chen, Yutong Wu, Chenyang Song +5
Grouped-Query Attention (GQA) is a widely adopted strategy for reducing the computational cost of attention layers in large language models (LLMs). However, current GQA configurati…
BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
Chenyang Song, Weilin Zhao, Xu Han +5
To alleviate the computational burden of large language models (LLMs), architectures with activation sparsity, represented by mixture-of-experts (MoE), have attracted increasing at…
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
Yuqi Luo, Chenyang Song, Xu Han +7
Activation sparsity denotes the existence of substantial weakly-contributed elements within activation outputs that can be eliminated, benefiting many important applications concer…
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models
Chenyang Song, Xu Han, Zhengyan Zhang +8
Activation sparsity refers to the existence of considerable weakly-contributed elements among activation outputs. As a prevalent property of the models using the ReLU activation fu…