MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts

• URL: http://arxiv.org/abs/2510.12357v1
• Date: Tue, 14 Oct 2025 10:22:44 GMT
• Title: MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts
• Authors: Yushu Zhao, Yubin Qin, Yang Wang, Xiaolong Yang, Huiming Han, Shaojun Wei, Yang Hu, Shouyi Yin,
• Abstract summary: 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.
• Score: 17.518573710849513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixture-of-Experts (MoE) models have recently demonstrated exceptional performance across a diverse range of applications. The principle of sparse activation in MoE models facilitates an offloading strategy, wherein active experts are maintained in GPU HBM, while inactive experts are stored in CPU DRAM. The efficacy of this approach, however, is fundamentally constrained by the limited bandwidth of the CPU-GPU interconnect. To mitigate this bottleneck, existing approaches have employed prefetching to accelerate MoE inference. These methods attempt to predict and prefetch the required experts using specially trained modules. Nevertheless, such techniques are often encumbered by significant training overhead and have shown diminished effectiveness on recent MoE models with fine-grained expert segmentation. In this paper, we propose MoBiLE, a plug-and-play offloading-based MoE inference framework with \textit{mixture of big-little experts}. It reduces the number of experts for unimportant tokens to half for acceleration while maintaining full experts for important tokens to guarantee model quality. Further, a dedicated fallback and prefetching mechanism is designed for switching between little and big experts to improve memory efficiency. We evaluate MoBiLE on four typical modern MoE architectures and challenging generative tasks. Our results show that MoBiLE achieves a speedup of 1.60x to 1.72x compared to the baseline on a consumer GPU system, with negligible degradation in accuracy.

Related papers

• PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference [17.441141633991197]
  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.
  arXiv  Detail & Related papers  (2025-11-06T20:53:02Z)
• 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)
• Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization [60.309915093470416]
  Matryoshka MoE (M-MoE) is a training framework that instills a coarse-to-fine structure directly into the expert ensemble.<n>Our work paves the way for more practical and adaptable deployments of large-scale MoE models.
  arXiv  Detail & Related papers  (2025-09-30T16:56:44Z)
• LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference [2.8653469160349077]
  We introduce LExI, a data-free optimization technique that determines the optimal number of active experts per layer in a pretrained MoE model.<n>Experiments on state-of-the-art language and vision MoE benchmarks demonstrate that LExI significantly outperforms traditional MoE pruning approaches in terms of inference efficiency.
  arXiv  Detail & Related papers  (2025-09-02T19:01:46Z)
• Enabling MoE on the Edge via Importance-Driven Expert Scheduling [21.860330824352527]
  MoE is a key technique for scaling Large Language Models by activating only a subset of experts per query.<n>We leverage expert importance to guide decisions, substituting low-cached activated experts with functionally similar ones already cached in GPU memory.<n>This design reduces memory usage and data transfer, while largely eliminating PCIe overhead.
  arXiv  Detail & Related papers  (2025-08-26T12:32:09Z)
• 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)
• Accelerating MoE Model Inference with Expert Sharding [1.4733737463429546]
  Mixture of experts (MoE) models achieve state-of-the-art results in language modeling but suffer from inefficient hardware utilization due to imbalanced token routing and communication overhead.<n>We introduce MoEShard, an inference system that achieves perfect load balancing through tensor sharding of MoE experts.
  arXiv  Detail & Related papers  (2025-03-11T14:15:01Z)
• Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading [7.9192039061119255]
  FineMoE is a fine-grained expert offloading system for MoE serving.<n>We show that FineMoE reduces inference latency by 47% and improves expert hit rate by 39% over state-of-the-art solutions.
  arXiv  Detail & Related papers  (2025-02-07T22:51:17Z)
• 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)
• A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts [49.394145046409044]
  This paper provides the first provably efficient technique for pruning experts in finetuned MoE models. We theoretically prove that prioritizing the pruning of the experts with a smaller change of the routers l2 norm from the pretrained model guarantees the preservation of test accuracy. Although our theoretical analysis is centered on binary classification tasks on simplified MoE architecture, our expert pruning method is verified on large vision MoE models.
  arXiv  Detail & Related papers  (2024-05-26T17:52:58Z)
• 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.