Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques

• URL: http://arxiv.org/abs/2406.02500v3
• Date: Mon, 17 Mar 2025 14:18:42 GMT
• Title: Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques
• Authors: Shwai He, Daize Dong, Liang Ding, Ang Li,
• Abstract summary: We present a holistic study of compression techniques for Mixture of Experts to enhance both efficiency and scalability.<n>We propose Layer Drop, which removes entire MoE layers, and Block Drop, which eliminates transformer blocks.<n>We also introduce Expert Slimming, which compresses individual experts to further boost performance and can be seamlessly integrated with Expert Trimming.
• Score: 17.436189502801163
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world deployment. The Mixture of Experts (MoE) architecture offers a promising solution by dynamically selecting and activating only a subset of experts during inference, thus substantially reducing computational costs while preserving high performance. Despite these benefits, MoE introduces new inefficiencies, such as excessive parameters and communication overhead. In this work, we present a holistic study of compression techniques for Mixture of Experts to enhance both efficiency and scalability. While recent efforts have focused on Expert Trimming, which reduces the number of experts, these approaches still suffer from considerable communication and computational costs. To address this, we propose more aggressive strategies, such as Layer Drop, which removes entire MoE layers, and Block Drop, which eliminates transformer blocks. Surprisingly, these aggressive pruning techniques not only preserve model performance but also substantially improve computation and memory efficiency. Furthermore, beyond Expert Trimming, we also introduce Expert Slimming, which compresses individual experts to further boost performance and can be seamlessly integrated with Expert Trimming. Extensive experimental results demonstrate the effectiveness of our proposed methods-Layer Drop and Block Drop-along with the comprehensive recipe that integrates Expert Slimming and Expert Trimming, achieving a 6.05x speedup with 77.1% reduced memory usage while maintaining over 92% of performance on Mixtral-8x7B. Our code is released at https://github.com/CASE-Lab-UMD/Unified-MoE-Compression.

Related papers

• Efficiently Editing Mixture-of-Experts Models with Compressed Experts [22.868004724309845]
  We propose the concept of compressed experts, lightweight modules that serve as compact representations of full experts. Our approach preserves the most important experts while replacing other auxiliary activated experts with compressed experts.
  arXiv  Detail & Related papers  (2025-03-01T22:00:03Z)
• HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference [54.40808356999408]
  We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency. HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.
  arXiv  Detail & Related papers  (2024-11-03T04:25:46Z)
• ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference [41.41316718220569]
  ExpertFlow is designed to enhance inference efficiency by accommodating flexible routing and enabling efficient expert scheduling between CPU and GPU. Our experiments demonstrate that ExpertFlow achieves up to 93.72% GPU memory savings and enhances inference speed by 2 to 10 times compared to baseline methods.
  arXiv  Detail & Related papers  (2024-10-23T15:24:54Z)
• EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search [33.86918407429272]
  We propose a new and general approach for dynamic compression that is provably optimal in a given input range. We show that these theoretical guarantees lead to highly competitive practical performance for dynamic compression of Llama, Mistral and Phi models.
  arXiv  Detail & Related papers  (2024-10-18T17:46:37Z)
• Mixture Compressor for Mixture-of-Experts LLMs Gains More [71.0473038084673]
  We propose a training-free Mixture-Compressor for Mixture-of-Experts large language models (MoE-LLMs) Our MC integrates static quantization and dynamic pruning to collaboratively achieve extreme compression for MoE-LLMs with less accuracy loss. For instance, at 2.54 bits, MC compresses 76.6% of the model, with only a 3.8% average accuracy loss.
  arXiv  Detail & Related papers  (2024-10-08T18:09:38Z)
• AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference [13.263938935671646]
  AdapMoE is an algorithm-system co-design framework for efficient MoE inference. AdapMoE features adaptive expert gating and management to reduce the on-demand loading overheads. We show AdapMoE consistently outperforms existing techniques, reducing the average number of activated experts by 25% and achieving a 1.35x speedup without degradation accuracy.
  arXiv  Detail & Related papers  (2024-08-19T03:27:15Z)
• MoDeGPT: Modular Decomposition for Large Language Model Compression [59.361006801465344]
  This paper introduces textbfModular bfDecomposition (MoDeGPT), a novel structured compression framework. MoDeGPT partitions the Transformer block into modules comprised of matrix pairs and reduces the hidden dimensions. Our experiments show MoDeGPT, without backward propagation, matches or surpasses previous structured compression methods.
  arXiv  Detail & Related papers  (2024-08-19T01:30:14Z)
• Mixture of A Million Experts [1.240096657086732]
  This paper introduces PEER, a novel layer design that utilizes the product key technique for sparse retrieval from a vast pool of experts. Experiments on language modeling tasks demonstrate that PEER layers outperform dense FFWs and coarse-grained MoEs in terms of performance-compute trade-off.
  arXiv  Detail & Related papers  (2024-07-04T20:59:20Z)
• Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs [30.07344792770254]
  We introduce a gradient-free evolutionary strategy named EEP (Efficient Expert Pruning) to enhance the pruning of experts in SMoE models. EEP relies solely on model inference (i.e., no gradient computation) and greater sparsity while maintaining or even improving performance on downstream tasks. We demonstrate that pruning up to 75% of experts in Mixtral $8times7$B-Instruct results in a substantial reduction in parameters with minimal performance loss.
  arXiv  Detail & Related papers  (2024-07-01T03:57:35Z)
• The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models [11.156816338995503]
  Large language models (LLMs) provide faster inference, smaller memory footprints, and enables local deployment. Two standard compression techniques are pruning and quantization, with the former eliminating redundant connections in model layers and the latter representing model parameters with fewer bits. Existing research on LLM compression primarily focuses on performance in terms of general metrics like perplexity or downstream task accuracy. More fine-grained metrics, such as those measuring parametric knowledge, remain significantly underexplored.
  arXiv  Detail & Related papers  (2023-12-01T22:27:12Z)
• Merging Experts into One: Improving Computational Efficiency of Mixture of Experts [71.44422347502409]
  A sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters. Can we retain the advantages of adding more experts without substantially increasing the computational costs? We propose a computation-efficient approach called textbftexttMerging Experts into One (MEO) which reduces the computation cost to that of a single expert.
  arXiv  Detail & Related papers  (2023-10-15T13:28:42Z)
• Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy [84.11508381847929]
  Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks. We propose M-SMoE, which leverages routing statistics to guide expert merging. Our MC-SMoE achieves up to 80% memory and a 20% FLOPs reduction, with virtually no loss in performance.
  arXiv  Detail & Related papers  (2023-10-02T16:51:32Z)
• MoEC: Mixture of Expert Clusters [93.63738535295866]
  Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated. However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation.
  arXiv  Detail & Related papers  (2022-07-19T06:09:55Z)
• Task-Specific Expert Pruning for Sparse Mixture-of-Experts [105.20605021416276]
  Mixture-of-Experts (MoE) model is powerful for large-scale pre-training. MoE is hard to be deployed on cloud or mobile environment. We propose a general method to progressively drop the non-professional experts for the target downstream task.
  arXiv  Detail & Related papers  (2022-06-01T07:09:01Z)
• Compression of Generative Pre-trained Language Models via Quantization [62.80110048377957]
  We find that previous quantization methods fail on generative tasks due to the textithomogeneous word embeddings We propose a token-level contrastive distillation to learn distinguishable word embeddings, and a module-wise dynamic scaling to make quantizers adaptive to different modules.
  arXiv  Detail & Related papers  (2022-03-21T02:11:35Z)
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient [88.58536093633167]
  Existing model compression approaches require re-compression or fine-tuning across diverse constraints to accommodate various hardware deployments. We propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere. Compared with state-of-the-art algorithms, YOCO-BERT provides more compact models, yet achieving 2.1%-4.5% average accuracy improvement on the GLUE benchmark.
  arXiv  Detail & Related papers  (2021-06-04T12:17:44Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)
• Neural Network Compression Via Sparse Optimization [23.184290795230897]
  We propose a model compression framework based on the recent progress on sparse optimization. We achieve up to 7.2 and 2.9 times FLOPs reduction with the same level of evaluation of accuracy on VGG16 for CIFAR10 and ResNet50 for ImageNet.
  arXiv  Detail & Related papers  (2020-11-10T03:03:55Z)
• GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework [94.26938614206689]
  We propose the first unified optimization framework combining multiple compression means for GAN compression, dubbed GAN Slimming. We apply GS to compress CartoonGAN, a state-of-the-art style transfer network, by up to 47 times, with minimal visual quality degradation.
  arXiv  Detail & Related papers  (2020-08-25T14:39:42Z)
• Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle [117.95823660228537]
  We propose a novel structured sparsification method for efficient network compression. The proposed method automatically induces structured sparsity on the convolutional weights. We also address the problem of inter-group communication with a learnable channel shuffle mechanism.
  arXiv  Detail & Related papers  (2020-02-19T12:03:10Z)

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.