paper-with-me

홈 › Papers

Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference

2024-11-27 · Andrii Skliar, Ties van Rozendaal, Romain Lepert, Todor Boinovski, Mart van Baalen, Markus Nagel, Paul Whatmough, Babak Ehteshami Bejnordi

Mixture of Experts (MoE) LLMs have recently gained attention for their ability to enhance performance by selectively engaging specialized subnetworks or "experts" for each input. However, deploying MoEs on memory-constrained devices remains challenging, particularly when generating tokens sequentially with a batch size of one, as opposed to typical high-throughput settings involving long sequences or large batches. In this work, we optimize MoE on memory-constrained devices where only a subset of expert weights fit in DRAM. We introduce a novel cache-aware routing strategy that leverages expert reuse during token generation to improve cache locality. We evaluate our approach on language modeling, MMLU, and GSM8K benchmarks and present on-device results demonstrating 2$\times$ speedups on mobile devices, offering a flexible, training-free solution to extend MoE's applicability across real-world applications.

📄 PDF Abstract BibTeX arXiv:2412.00099

Code (0)

등록된 구현이 없습니다.

Tasks

GSM8KLanguage ModelingLanguage ModellingMixture-of-ExpertsMMLU

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
MoE 설명 없음

Similar Papers 제목 키워드 기반

MobileMoE: Scaling On-Device Mixture of Experts

2026-05-26 · Yanbei Chen, Hanxian Huang, Ernie Chang, Jacob Szwejbka 외 arxiv

Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language models, yet its advantages at sub-billion scales for on-device deployment remain largely unexplored. To close this gap,…

Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models

2025-05-21 · Jingcong Liang, Siyuan Wang, Miren Tian, Yitong Li 외

Mixture-of-Experts (MoE) enables efficient scaling of large language models (LLMs) with sparsely activated experts during inference. To effectively deploy large MoE models on memory-constrained devices, many systems intr…

AllCPUMixture-of-Experts

Mixture of Lookup Key-Value Experts

2025-12-10 · Zongcheng Wang arxiv

Recent research has developed several LLM architectures suitable for inference on end-user devices, such as the Mixture of Lookup Experts (MoLE)~\parencite{jie_mixture_2025}. A key feature of MoLE is that each token id i…

FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices

2026-01-22 · Byeongju Kim, Jungwan Lee, Donghyeon Han, Hoi-Jun Yoo 외 arxiv

Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation enables inference to be performed by acces…

SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution

2025-08-26 · Guoying Zhu, Meng Li, Haipeng Dai, Xuechen Liu 외 arxiv

The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consumer-grade edge hardware, however, is cons…