Beacon: Post-Training Quantization with Integrated Grid Selection
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Language Modeling | WikiText-2 | Perplexity (PPL)7.53 | 2862 | |
| Image Classification | ImageNet (val) | -- | 1206 | |
| Language Modeling | WikiText-2 (val) | Perplexity (BVS)21.9 | 179 | |
| Commonsense Reasoning | ARC-Easy, ARC-Challenge, and HellaSwag Average | Zero-Shot Accuracy36.8 | 60 | |
| Zero-shot Evaluation | Zero-shot Benchmarks Average | Average Accuracy59.7 | 60 | |
| Image Classification | ImageNet (val) | Accuracy Drop0.34 | 12 |