Preprint
Jul 2026
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
WIDE is presented, the first end-to-end differentiable token-level dynamic width pruning framework designed for both prefill and decode scenarios, and a pruning--kernel co-design framework that decomposes dynamic sparsity acceleration into mask reordering, hardware-agnostic block-level skipping, and hardware-dependent intra-block skipping, enabling efficient execution across different granularities.
Haozhe Hu, Hao Wu, Pei-Ran Yin et al.
· 1 citation