DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs
This addresses deployment challenges for LLMs by improving efficiency without retraining, though it is incremental as it builds on existing pruning methods.
The paper tackles the problem of high memory and compute costs in large language models (LLMs) by proposing DuoGPT, a training-free dual sparsity framework that combines unstructured weight pruning with activation sparsity, resulting in up to 9.17% higher accuracy at a 1.39x speedup compared to dense models.
Large language models (LLMs) deliver strong performance but are difficult to deploy due to high memory and compute costs. While pruning reduces these demands, most methods ignore activation sparsity observed at runtime. We reinterpret activation sparsity as dynamic structured weight sparsity and propose DuoGPT, a unified framework that constructs dual-sparse (spMspV) workloads by combining unstructured weight pruning with activation sparsity. To preserve accuracy, we extend the Optimal Brain Compression (OBC) framework with activation-aware calibration and introduce output residuals from the dense model as correction terms. We further optimize the solution for efficient GPU execution, enabling scalability to billion-parameter LLMs. Evaluations on LLaMA-2 and LLaMA-3 show that DuoGPT outperforms state-of-the-art structured pruning methods by up to 9.17% accuracy at an iso-speedup of 1.39$\times$ compared to the baseline dense model. Code is available at Github.