PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models
This work addresses the challenge of optimizing sparse models for efficient deployment, though it is incremental as it builds on existing pruning methods.
The paper tackles the problem of improving accuracy in N:M sparse large language models by proposing PermLLM, a post-training pruning framework that uses learnable channel permutation to better retain important weights, achieving superior performance on models like LLaMA, Qwen, and OPT.
Channel permutation is a powerful technique for enhancing the accuracy of N:M sparse models by reordering the channels of weight matrices to prioritize the retention of important weights. However, traditional channel permutation methods rely on handcrafted quality metrics, which often fail to accurately capture the true impact of pruning on model performance. To address this limitation, we propose PermLLM, a novel post-training pruning framework that introduces learnable channel permutation (LCP) for N:M sparsity. LCP leverages Sinkhorn normalization to transform discrete permutation matrices into differentiable soft permutation matrices, enabling end-to-end optimization. Additionally, PermLLM incorporates an efficient block-wise channel permutation strategy, which significantly reduces the number of learnable parameters and computational complexity. PermLLM seamlessly integrates with existing one-shot pruning methods to adaptively optimize channel permutations, effectively mitigating pruning-induced errors. Extensive experiments on the LLaMA series, Qwen, and OPT models demonstrate that PermLLM achieves superior performance in optimizing N:M sparse models. The code is available at https://github.com/lanchengzou/PermLLM.