Sink-Aware Pruning for Diffusion Language Models
Aidar Myrzakhan Tianyi Li Bowei Guo Shengkun Tang Zhiqiang Shen
作者信息
Abstract
Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited from autoregressive (AR) LLMs, typically preserve attention sink tokens because AR sinks serve as stable global anchors. We show that this assumption does not hold for DLMs: the attention-sink position exhibits substantially higher variance over the full generation trajectory (measured by how the dominant sink locations shift across timesteps), indicating that sinks are often transient and less structurally essential than in AR models. Based on this observation, we propose ${\bf \texttt{Sink-Aware Pruning}}$, which automatically identifies and prunes unstable sinks in DLMs (prior studies usually keep sinks for AR LLMs). Without retraining, our method achieves a better quality-efficiency trade-off and outperforms strong prior pruning baselines under matched compute. Our code is available at https://github.com/VILA-Lab/Sink-Aware-Pruning.引用本文复制引用
Aidar Myrzakhan,Tianyi Li,Bowei Guo,Shengkun Tang,Zhiqiang Shen.Sink-Aware Pruning for Diffusion Language Models[EB/OL].(2026-02-19)[2026-02-22].https://arxiv.org/abs/2602.17664.学科分类
计算技术、计算机技术
|国家预印本平台
评论