无需调参的量化方法，自动选择最优缩放因子
Beacon: Post-Training Quantization with Integrated Grid Selection
- 直接使用未缩放网格进行每通道量化，自动确定最佳缩放因子
- 在不依赖反向传播和大校准集的前提下达到顶尖性能
- 适合需要快速部署、无需调参的工程场景
量化是降低大型预训练模型内存与计算开销的常用压缩技术。每通道后训练量化（PTQ）的关键挑战在于选择合适的缩放因子，以将权重值替换为缩放整数网格中的值。现有方法通常通过启发式调参或网格搜索在初始阶段固定缩放因子。我们提出Beacon，一种简单有效的算法，无需手动调参。Beacon直接使用未缩放网格执行每通道PTQ，通过利用标量量化几何结构自动确定最优缩放因子，不依赖反向传播或大规模校准集。尽管简单且无需调参，Beacon在性能上仍可媲美最先进方法，成为高效模型部署的实用方案。
原文摘要 · Abstract (English)
Quantization is a widely used compression technique for reducing the memory and computation costs of large pre-trained models. A key challenge in per-channel post-training quantization (PTQ) is selecting appropriate scaling factors to replace weight values with values from a scaled integer grid. Existing methods typically fix the scale at the outset via heuristic tuning or grid search. We propose Beacon, a simple and effective algorithm that eliminates the need for such manual tuning. Beacon performs per-channel PTQ directly using an unscaled grid and automatically determines the optimal scaling factors by exploiting the geometry of scalar quantization. It does not rely on back-propagation or large calibration sets. Despite its simplicity and tuning-free nature, Beacon achieves competitive performance compared to state-of-the-art methods, making it a practical solution for efficient model deployment.
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。