Beacon: Post-Training Quantization with Integrated Grid Selection
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911451553202176 |
|---|---|
| author | Zhang, Shihao Saab, Rayan |
| author_facet | Zhang, Shihao Saab, Rayan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_20293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beacon: Post-Training Quantization with Integrated Grid Selection Zhang, Shihao Saab, Rayan Machine Learning Artificial Intelligence 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. |
| title | Beacon: Post-Training Quantization with Integrated Grid Selection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.20293 |