速度即一切:通过GPU感知优化实现大型扩散模型的端侧加速
Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations
AI总结:
针对大型扩散模型端侧部署受计算和内存资源限制的问题,提出GPU感知的实现优化方案,在移动设备上实现了当前最快的扩散模型推理延迟,拓展了生成式AI的适用场景。
摘要:
基础模型的快速发展与应用已彻底改变了人工智能领域。大型扩散模型凭借生成逼真图像、支持多种任务的能力受到广泛关注。这类模型的端侧部署具备降低服务器成本、支持离线功能、提升用户隐私性等优势。然而,常见的大型扩散模型参数规模超10亿,受限于设备端有限的计算与内存资源,部署面临挑战。我们提出了一系列针对大型扩散模型的实现优化方案,在搭载GPU的移动设备上实现了目前已公开的最快推理延迟——在三星S23 Ultra设备上,针对512×512图像、20步迭代的Stable Diffusion 1.4(无int8量化)推理耗时低于12秒。这些优化拓展了生成式AI的适用范围,提升了各类设备上的整体用户体验。
英文摘要:
The rapid development and application of foundation models have revolutionized the field of artificial intelligence. Large diffusion models have gained significant attention for their ability to generate photorealistic images and support various tasks. On-device deployment of these models provides benefits such as lower server costs, offline functionality, and improved user privacy. However, common large diffusion models have over 1 billion parameters and pose challenges due to restricted computational and memory resources on devices. We present a series of implementation optimizations for large diffusion models that achieve the fastest reported inference latency to-date (under 12 seconds for Stable Diffusion 1.4 without int8 quantization on Samsung S23 Ultra for a 512x512 image with 20 iterations) on GPU-equipped mobile devices. These enhancements broaden the applicability of generative AI and improve the overall user experience across a wide range of devices.
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。