Beacon: Post-Training Quantization with Integrated Grid Selection
Beacon: Post-Training Quantization with Integrated Grid Selection
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.
Shihao Zhang、Rayan Saab
计算技术、计算机技术
Shihao Zhang,Rayan Saab.Beacon: Post-Training Quantization with Integrated Grid Selection[EB/OL].(2025-09-04)[2025-09-06].https://arxiv.org/abs/2508.20293.点此复制
评论