The growing size of large language models has created significant computational inefficiencies. To address this challenge, sparse activation methods selectively deactivates non-essential parameters during inference, reducing computational costs in FFNN layers. While existing methods focus on non-linear gating mechanisms, we hypothesize that the sparsity of the FFNN layer lies globally in the form of a linear combination over its internal down projection matrix. Based on this insight, we propose two methods: M-COUNTDOWN, leveraging indirect coefficients, and D-COUNTDOWN, utilizing direct coefficients of the linear combination. Experimental results demonstrate that D-COUNTDOWN can omit 90% of computations with performance loss as low as 5.5% ideally, while M-COUNTDOWN provides a predictor-free solution with up to 29.4% better performance preservation compared to existing methods. Our specialized kernel implementations effectively realize these theoretical gains into substantial real-world acceleration.
@article{arxiv.2505.17701,
title = {COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection},
author = {Jaewon Cheon and Pilsung Kang},
journal= {arXiv preprint arXiv:2505.17701},
year = {2025}
}