4 papers
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
Haozhe Hu, Hao Wu, Peiran Yin +3
Pruning is a promising approach for improving the efficiency of large language models (LLMs). Static structured pruning is hardware-friendly, but its input-agnostic computation all…
Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models
Chao Han, Haozhe Hu, Xiaoyu Shen
Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance d…
UniRank: Unified Rank Allocation for Low-Rank LLM Compression
Chao Han, Haozhe Hu, Yongjie Du +5
Low-rank decomposition is a promising compression paradigm for large language models (LLMs), yet its effectiveness hinges on rank budget allocation across weight matrices: uniform…
Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
Chao Han, Yijuan Liang, Zihao Xuan +3
The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computa…