Compressing LLMs with MoP: Mixture of Pruners

• URL: http://arxiv.org/abs/2602.06127v1
• Date: Thu, 05 Feb 2026 19:01:06 GMT
• Title: Compressing LLMs with MoP: Mixture of Pruners
• Authors: Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Victor Zacarias, Leandro Giusti Mugnaini, Keith Ando Ogawa, Lucas Pellicer, Rosimeire Pereira Costa, Edson Bollis, Anna Helena Reali Costa, Artur Jordao,
• Abstract summary: MoP (Mixture of Pruners) is an iterative framework for model pruning.<n>It consistently outperforms depth-only and width-only pruning.<n>It translates into real speedup, reducing end-to-end latency by 39% at 40% compression.
• Score: 0.5727968722424193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference. In response, model pruning emerges as an effective strategy, yet current methods typically focus on a single dimension-depth or width. We introduce MoP (Mixture of Pruners), an iterative framework that unifies these dimensions. At each iteration, MoP generates two branches-pruning in depth versus pruning in width-and selects a candidate to advance the path. On LLaMA-2 and LLaMA-3, MoP advances the frontier of structured pruning, exceeding the accuracy of competing methods across a broad set of compression regimes. It also consistently outperforms depth-only and width-only pruning. Furthermore, MoP translates structural pruning into real speedup, reducing end-to-end latency by 39% at 40% compression. Finally, extending MoP to the vision-language model LLaVA-1.5, we notably improve computational efficiency and demonstrate that text-only recovery fine-tuning can restore performance even on visual tasks.

Related papers

• Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog [72.4168434368873]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources.<n>We propose a gradual compacting method that divides the compression process into multiple fine-grained iterations.<n>This iterative approach-reminiscent of the "boiling frog" effect-enables the model to be progressively compressed without abrupt performance loss.
  arXiv  Detail & Related papers  (2026-02-04T06:56:52Z)
• SwiftPrune: Hessian-Free Weight Pruning for Large Language Models [42.36642747110806]
  Post-training pruning is one of the key techniques for compressing large language models.<n>SwiftPrune is a novel Hessian-free weight pruning method that achieves hardware-efficient model compression.<n>We show that SwiftPrune completes the pruning process within seconds, achieving an average speedup of 12.29x (up to 56.02x) over existing SOTA approaches.
  arXiv  Detail & Related papers  (2025-01-24T02:50:13Z)
• FASP: Fast and Accurate Structured Pruning of Large Language Models [24.185245582500876]
  We introduce FASP (Fast and Accurate Structured Pruning), a novel structured pruning framework for large language models (LLMs)<n>FASP employs a distinctive pruning structure that interlinks sequential layers, allowing for the removal of columns in one layer while simultaneously eliminating corresponding rows in the preceding layer without incurring additional performance loss.<n>We evaluate FASP on the OPT and LLaMA model families, demonstrating superior performance in terms of perplexity and accuracy on downstream tasks compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-16T09:38:39Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning that learns the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model.<n>We achieve this by learning an underlying Bernoulli distribution to sample binary pruning masks.<n>Experiments conducted on LLaMA, LLaMA-2, LLaMA-3, Vicuna, and Mistral models demonstrate the promising performance of our method in efficiency and effectiveness.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric [57.3330687266266]
  We find that using smaller pre-trained models and applying magnitude-based pruning on CLIP models leads to inflexibility and inferior performance. Using the Module-wise Pruning Error (MoPE) metric, we introduce a unified pruning framework applicable to both pre-training and task-specific fine-tuning compression stages.
  arXiv  Detail & Related papers  (2024-03-12T17:24:26Z)
• BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation [54.28841287750586]
  Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. Existing solutions such as SparseGPT and Wanda attempt to alleviate this issue through weight pruning. This paper introduces a novel LLM pruning technique dubbed blockwise parameter-efficient sparsity allocation (BESA) by applying a blockwise reconstruction loss.
  arXiv  Detail & Related papers  (2024-02-18T12:44:15Z)
• Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods [5.135352292810664]
  We show that simple depth pruning can effectively compress large language models (LLMs) Our pruning method boosts inference speeds, especially under memory-constrained conditions. We hope this work can help build compact yet capable LLMs.
  arXiv  Detail & Related papers  (2024-02-05T09:44:49Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models [78.45898846056303]
  Pruning is an effective method to reduce the memory footprint and computational cost associated with large natural language processing models. We develop a novel MultiLevel structured Pruning framework, which uses three different levels of structured pruning: head pruning, row pruning, and block-wise sparse pruning.
  arXiv  Detail & Related papers  (2021-05-30T22:00:44Z)

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.