按需动态加载模型块，显著提升边缘设备多任务切换速度。
On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices
- 将模型权重拆分为可复用的块单元，跨任务对齐稀疏结构。
- 任务切换时仅加载差异块，平均提速6.6倍以上。
- 适合资源受限的边缘多任务部署场景。
稀疏化是将大型模型部署到资源受限边缘平台的关键。然而，孤立优化各任务的稀疏模式会忽略频繁任务切换带来的显著输入输出开销。本文提出一种按需多任务稀疏框架，通过最大化参数复用以最小化切换成本。不同于整体式方法，我们将权重分解为可复用的块粒度单元，并对齐各任务间的稀疏结构以最大化重叠。通过仅动态加载下一任务所需的少量差异块，有效缓解传统整体式方法固有的冷启动延迟。在真实自动驾驶平台上的实验表明，该框架在任务切换效率上表现卓越，相比现有稀疏方法平均加速超过6.6倍。
原文摘要 · Abstract (English)
Sparsity is essential for deploying large models on resource constrained edge platforms. However, optimizing sparsity patterns for individual tasks in isolation ignores the significant I/O overhead incurred during frequent task switching. We introduce an on-demand multi-task sparsity framework specifically designed to minimize switching costs by maximizing parameter reuse. Unlike monolithic approaches, we decompose weights into reusable block-granular units and align sparse structures across tasks to maximize overlap. By dynamically loading only the small differential set of blocks required for the next task, our method effectively mitigates the cold-start latency inherent in traditional monolithic approaches.Experiments on a real-world autonomous driving platform demonstrate that our framework achieves superior switching efficiency, accelerating task switching by over 6.6X on average compared to existing sparsity methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。