Neuralink：基于神经元共激活链接的智能手机快速LLM推理
Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
AI总结：
提出Neuralink方法，通过优化闪存中神经元放置并利用神经元共激活概念，加速智能手机上的LLM推理，实现端到端延迟平均1.49倍提升。
摘要：
大型语言模型（LLM）在各个领域取得了显著成功，但由于其庞大的计算和内存需求，将它们部署在移动设备上是一项艰巨的任务。轻量级LLM虽被开发以适应移动环境，但模型准确性有所下降。相比之下，基于稀疏性的技术通过仅将相关神经元选择性地传输到DRAM，同时将完整模型保留在外部存储（如闪存）中，从而最小化DRAM使用。然而，此类方法受限于大量I/O操作，尤其是在IOPS受限严重的智能手机上。本文提出Neuralink，一种通过优化闪存中神经元放置来加速智能手机LLM推理的新方法。Neuralink利用神经元共激活概念，将频繁共同激活的神经元链接起来，以促进连续读取访问并优化I/O效率。该方法包含两阶段方案：离线阶段根据共激活模式重组神经元放置；在线阶段采用定制的数据访问和缓存策略以匹配硬件特性。在多款智能手机和LLM上进行的评估表明，Neuralink在端到端延迟上平均实现了1.49倍的提升。作为首个优化稀疏性下存储布局的解决方案，Neuralink探索了稀疏驱动算法与存储级系统协同设计在LLM推理交叉点的新优化空间。
英文摘要：
Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge due to their extensive computational and memory demands. While lightweight LLMs have been developed to fit mobile environments, they suffer from degraded model accuracy. In contrast, sparsity-based techniques minimize DRAM usage by selectively transferring only relevant neurons to DRAM while retaining the full model in external storage, such as flash. However, such approaches are critically limited by numerous I/O operations, particularly on smartphones with severe IOPS constraints. In this paper, we propose Neuralink, a novel approach that accelerates LLM inference on smartphones by optimizing neuron placement in flash memory. Neuralink leverages the concept of Neuron Co-Activation, where neurons frequently activated together are linked to facilitate continuous read access and optimize I/O efficiency. Our approach incorporates a two-stage solution: an offline stage that reorganizes neuron placement based on co-activation patterns, and an online stage that employs tailored data access and caching strategies to align well with hardware characteristics. Evaluations conducted on a variety of smartphones and LLMs demonstrate that Neuralink achieves on average $1.49\times$ improvements in end-to-end latency compared to the state-of-the-art. As the first solution to optimize storage placement under sparsity, Neuralink explores a new optimization space at the intersection of sparsity-driven algorithm and storage-level system co-design for LLM inference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
