{"ID":2877822,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20293","arxiv_id":"2508.20293","title":"Beacon: Post-Training Quantization with Integrated Grid Selection","abstract":"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.","short_abstract":"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 typica...","url_abs":"https://arxiv.org/abs/2508.20293","url_pdf":"https://arxiv.org/pdf/2508.20293v2","authors":"[\"Shihao Zhang\",\"Rayan Saab\"]","published":"2025-08-27T22:00:18Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}