works on
dynamic pruning 1large language models 1model compression 1model efficiency 1token-level inference 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

Haozhe Hu, Hao Wu, Peiran Yin +3

WIDE introduces a token-level dynamic width pruning framework for large language model inference, allowing each token to selectively activate attention heads and feed‑forward chann…