Kaihao Huang

Xuan Ding, Rui Sun, Yunjian Zhang et al.

Compared to width-wise pruning, depth-wise pruning can significantly accelerate inference in resource-constrained scenarios. However, treating the entire Transformer layer as the minimum pruning unit may degrade model performance by indiscriminately discarding the entire information of the layer. This paper reveals the ``Patch-like'' feature relationship between layers in large language models by analyzing the correlation of the outputs of different layers in the reproducing kernel Hilbert space. Building on this observation, we propose a sliding layer merging method that dynamically selects and fuses consecutive layers from top to bottom according to a pre-defined similarity threshold, thereby simplifying the model structure while maintaining its performance. Extensive experiments on LLMs with various architectures and different parameter scales show that our method outperforms existing pruning techniques in both zero-shot inference performance and retraining recovery quality after pruning. In particular, in the experiment with 35% pruning on the Vicuna-7B model, our method achieved a 1.654% improvement in average performance on zero-shot tasks compared to the existing method. Moreover, we further reveal the potential of combining depth pruning with width pruning to enhance the pruning effect. Our codes are available at https://github.com/920927/SLM-a-sliding-layer-merging-method.

Xuan Ding, Rui Sun, Yunjian Zhang et al.

The ever-increasing computational demands and deployment costs of large language models (LLMs) have spurred numerous compressing methods. Compared to quantization and unstructured pruning, SVD compression offers superior hardware compatibility and theoretical guarantees. However, existing SVD-based methods focus on the overall discrepancy between the original and compressed matrices while overlooking the protection of critical components within the matrix, which leads to inferior performance in the compressed models. This paper proposes a dual-level importance protection mechanism to enhance SVD-based compression methods: (1) local importance protection: preserving the most critical singular vectors within each weight matrix through channel-weighted data whitening; and (2) global importance protection: enabling less important layers to bear a greater portion of the compression burden through either a heuristic or optimization-based approach, thereby minimizing the impact of compression on critical layers. Extensive experiments demonstrate that DipSVD outperforms existing SVD-based compression approaches across multiple benchmarks, achieving superior model performance especially at high model compression ratios.