PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference

• URL: http://arxiv.org/abs/2511.04805v1
• Date: Thu, 06 Nov 2025 20:53:02 GMT
• Title: PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
• Authors: Yushu Zhao, Zheng Wang, Minjia Zhang,
• Abstract summary: We introduce PuzzleMoE, a training-free MoE compression method that achieves high accuracy and efficient inference through two key innovations.<n>First, PuzzleMoE performs sparse expert merging by identifying element-wise weight redundancy and specialization.<n>Second, to avoid the overhead of storing binary masks and signs, PuzzleMoE introduces a bit-packed encoding scheme that reuses underutilized exponent bits.
• Score: 17.441141633991197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input. However, their widespread deployment remains limited due to the high memory overhead associated with storing all expert parameters, particularly as the number of experts increases. To address this challenge, prior works have explored expert dropping and merging strategies, yet they often suffer from performance drop at high compression ratios. In this paper, we introduce PuzzleMoE, a training-free MoE compression method that achieves both high accuracy and efficient inference through two key innovations: First, PuzzleMoE performs sparse expert merging by identifying element-wise weight redundancy and specialization. It uses a dual-mask to capture both shared and expert-specific parameters. Second, to avoid the overhead of storing binary masks and signs, PuzzleMoE introduces a bit-packed encoding scheme that reuses underutilized exponent bits, enabling efficient MoE inference on GPUs. Extensive experiments demonstrate that PuzzleMoE can compress MoE models by up to 50% while maintaining accuracy across various tasks. Specifically, it outperforms prior MoE compression methods by up to 16.7% on MMLU at 50% compression ratio, and achieves up to 1.28\times inference speedup.

Related papers

• MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts [17.518573710849513]
  MoBiLE is a plug-and-play offloading-based MoE inference framework with textitmixture of big-little experts.<n>MoBiLE achieves a speedup of 1.60x to 1.72x compared to the baseline on a consumer GPU system, with negligible degradation in accuracy.
  arXiv  Detail & Related papers  (2025-10-14T10:22:44Z)
• MC#: Mixture Compressor for Mixture-of-Experts Large Models [86.64315380917827]
  Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation.<n>We propose MC# (Mixture-Compressor-sharp), a framework that combines static quantization and dynamic expert pruning.
  arXiv  Detail & Related papers  (2025-10-13T03:12:46Z)
• CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis [55.099051077903766]
  Large Language Models with Mixture-of-Experts (MoE) suffer from substantial computational and storage overheads.<n>We introduce micro-expert as a finer-grained compression unit that spans across matrices.<n>We propose CAMERA-P, a structured micro-expert pruning framework, and CAMERA-Q, a mixed-precision quantization idea designed for micro-experts.
  arXiv  Detail & Related papers  (2025-08-04T11:42:48Z)
• MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models [36.730689832979365]
  MoTE is a scalable and memory-efficient approach to train Mixture-of-Ternary-Experts models from dense checkpoint.<n>MoTE achieves comparable performance to full-precision baseline MoE-LLaVA while offering lower memory footprint.
  arXiv  Detail & Related papers  (2025-06-17T11:53:49Z)
• Mixture of Lookup Experts [63.787712153454464]
  Mixture-of-Experts (MoE) activates only a subset of experts during inference.<n>MoLE is a new MoE architecture that is efficient in both communication and VRAM usage.
  arXiv  Detail & Related papers  (2025-03-20T02:31:57Z)
• ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration [61.579842548990754]
  Mixture-of-Experts (MoE) Transformer, the backbone of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for each input token.<n>We introduce ResMoE, an innovative MoE approximation framework that utilizes Wasserstein barycenter to extract a common expert (barycenter expert) and approximate the residuals between this barycenter expert and the original ones.
  arXiv  Detail & Related papers  (2025-03-10T03:15:54Z)
• 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)<n>Our MC integrates static quantization and dynamic pruning to collaboratively achieve extreme compression for MoE-LLMs with less accuracy loss.<n>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)
• BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts [41.83123857437985]
  Training MoEs from scratch in a large-scale regime is prohibitively expensive. We propose BAM (Branch-Attend-Mix), a simple yet effective method that addresses this shortcoming. Our experiments on seed models ranging from 590 million to 2 billion parameters demonstrate that BAM surpasses baselines in both perplexity and downstream task performance.
  arXiv  Detail & Related papers  (2024-08-15T17:19:12Z)
• Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques [17.436189502801163]
  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.
  arXiv  Detail & Related papers  (2024-06-04T17:18:40Z)
• 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)

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.