Efficient LLMs with AMP: Attention Heads and MLP Pruning

• URL: http://arxiv.org/abs/2504.21174v1
• Date: Tue, 29 Apr 2025 20:50:08 GMT
• Title: Efficient LLMs with AMP: Attention Heads and MLP Pruning
• Authors: Leandro Giusti Mugnaini, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Victor Zacarias, Edson Bollis, Lucas Pellicer, Anna Helena Reali Costa, Artur Jordao,
• Abstract summary: We introduce AMP: Attention Heads and Pruning, a novel structured pruning method that efficiently compresses Large Language Models (LLMs)<n>By projecting the input data onto weights, AMP assesses structural importance and overcomes the limitations of existing techniques.<n> AMP surpasses the current state-of-the-art on commonsense reasoning tasks by up to 1.49 percentage points.
• Score: 1.3785656730024138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning drives a new wave in computing systems and triggers the automation of increasingly complex problems. In particular, Large Language Models (LLMs) have significantly advanced cognitive tasks, often matching or even surpassing human-level performance. However, their extensive parameters result in high computational costs and slow inference, posing challenges for deployment in resource-limited settings. Among the strategies to overcome the aforementioned challenges, pruning emerges as a successful mechanism since it reduces model size while maintaining predictive ability. In this paper, we introduce AMP: Attention Heads and MLP Pruning, a novel structured pruning method that efficiently compresses LLMs by removing less critical structures within Multi-Head Attention (MHA) and Multilayer Perceptron (MLP). By projecting the input data onto weights, AMP assesses structural importance and overcomes the limitations of existing techniques, which often fall short in flexibility or efficiency. In particular, AMP surpasses the current state-of-the-art on commonsense reasoning tasks by up to 1.49 percentage points, achieving a 30% pruning ratio with minimal impact on zero-shot task performance. Moreover, AMP also improves inference speeds, making it well-suited for deployment in resource-constrained environments. We confirm the flexibility of AMP on different families of LLMs, including LLaMA and Phi.

Related papers

• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs.<n> Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing [14.114970711442512]
  This paper introduces Attention Pruning, a fairness-aware simulated annealing approach to prune attention heads in large language models (LLMs)<n>Our experiments show that Attention Pruning achieves up to $40%$ reduction in gender bias and outperforms the state-of-the-art bias mitigation strategies.
  arXiv  Detail & Related papers  (2025-03-20T03:02:32Z)
• Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout [15.009864792277236]
  Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. This work proposes DropPEFT, an innovative federated PEFT framework that employs a novel transformer dropout method. We show that DropPEFT can achieve a 1.3-6.3times speedup in model convergence and a 40%-67% reduction in memory footprint.
  arXiv  Detail & Related papers  (2025-03-13T09:59:16Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs [22.177654792824896]
  We focus on small-sized language models (3B to 7B parameters) for their cost-efficiency and accessibility.<n>We explore various training configurations and strategies across four open-source pre-trained models.<n>Key insights from our work include: (i) larger batch sizes paired with lower learning rates lead to improved model performance on benchmarks such as MMLU, MTBench, and Open LLM Leaderboard; (ii) early-stage training dynamics, such as lower gradient norms and higher loss values, are strong indicators of better final model performance; (iv) we observed no significant difference in performance between phased and stacked training strategies, but
  arXiv  Detail & Related papers  (2024-12-17T21:16:59Z)
• OP-LoRA: The Blessing of Dimensionality [93.08208871549557]
  Low-rank adapters enable fine-tuning of large models with only a small number of parameters. They often pose optimization challenges, with poor convergence. We introduce an over- parameterized approach that accelerates training without increasing inference costs. We achieve improvements in vision-language tasks and especially notable increases in image generation.
  arXiv  Detail & Related papers  (2024-12-13T18:55:19Z)
• Activation Sparsity Opportunities for Compressing General Large Language Models [4.5624217435826]
  This work systematically investigates the tradeoff between enforcing activation sparsity and perplexity (accuracy) on state-of-the-art AI models. Our empirical analysis demonstrates that we can obtain around 50% of main memory and computing reductions for critical FFN components with negligible accuracy degradation.
  arXiv  Detail & Related papers  (2024-12-13T02:26:54Z)
• Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning [104.27224674122313]
  Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions.
  arXiv  Detail & Related papers  (2024-11-17T01:16:37Z)
• Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs [12.250524667536606]
  Large language models (LLMs) still suffer from the challenging extrapolation problem. We conduct a theoretical analysis to better understand why No Position. (NoPE) fails outside its effective range, as well as examining the power of Position. (PE) in this context. We introduce a novel weave PE method, MesaExtrapolation, which utilizes a chunk-based triangular attention matrix and applies Stair-Extrapolation to manage the final chunk.
  arXiv  Detail & Related papers  (2024-10-21T10:39:05Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models [42.95555008229016]
  We propose a method based on Hessian sensitivity-aware mixed sparsity pruning to prune LLMs to at least 50% sparsity without the need of any retraining. The advantages of the proposed method exhibit even more when the sparsity is extremely high.
  arXiv  Detail & Related papers  (2023-10-14T05:43:09Z)
• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
  Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs. We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting. Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
  arXiv  Detail & Related papers  (2023-05-22T17:02:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.