量化与统一自适应蒸馏用于在边缘设备上实现多LoRA基于的通用生成视觉模型
Quantization with Unified Adaptive Distillation to enable multi-LoRA based one-for-all Generative Vision Models on edge
AI总结：
本文提出统一框架，通过单共享模型在边缘设备上实现多任务生成式AI推理，采用动态任务切换和QUAD量化策略，减少内存占用和延迟，保持高质量生成效果。
摘要：
生成式人工智能（GenAI）特性如图像编辑、物体移除和提示引导图像转换正越来越多地集成到移动应用中。然而，由于其高内存和计算需求，将大型视觉模型（LVMs）部署到资源受限设备上仍然具有挑战性。虽然低秩适配器（LoRAs）能够实现参数高效的任务适应，但现有的移动部署流程通常为每个LoRA加上基础模型的副本编译单独的模型二进制文件，导致存储冗余和运行时开销增加。在本文中，我们提出了一种统一框架，用于在边缘设备上通过单个共享模型实现多任务GenAI推理。我们的核心思想是将LoRA权重作为运行时输入，而不是嵌入到编译模型图中，从而在运行时动态切换任务而无需重新编译。然后，为了支持高效的设备执行，我们引入QUAD（量化与统一自适应蒸馏），一种量化感知训练策略，使多个LoRA适配器在共享量化配置下对齐。我们实现了所提出的系统，使用轻量级运行时栈，与移动NPUs兼容，并在多个芯片组上进行了评估。实验结果表明，内存占用减少了6倍，延迟改进了4倍，同时在多个GenAI任务中保持了高质量的视觉效果。
英文摘要：
Generative Artificial Intelligence (GenAI) features such as image editing, object removal, and prompt-guided image transformation are increasingly integrated into mobile applications. However, deploying Large Vision Models (LVMs) for such tasks on resource-constrained devices remains challenging due to their high memory and compute requirements. While Low-Rank Adapters (LoRAs) enable parameter-efficient task adaptation, existing Mobile deployment pipelines typically compile separate model binaries for each LoRA + a copy of the foundation model, resulting in redundant storage and increased runtime overhead. In this work, we present a unified framework for enabling multi-task GenAI inference on edge devices using a single shared model. Our key idea is to treat LoRA weights as runtime inputs rather than embedding them into the compiled model graph, allowing dynamic task switching at runtime without recompilation. Then, to support efficient on-device execution, we introduce QUAD (Quantization with Unified Adaptive Distillation), a quantizationaware training strategy that aligns multiple LoRA adapters under a shared quantization profile. We implement the proposed system with a lightweight runtime stack compatible with mobile NPUs and evaluate it across multiple chipsets. Experimental results demonstrate up to 6x and 4x reduction in memory footprint and latency improvements, respectively, while maintaining high visual quality across multiple GenAI tasks.
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。
