SOURCE-LINKED INTELLIGENCE

DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs

arXiv · AI, language, vision and robotics · article · Oct 9, 2026 · UTC

Low-bit inference on accelerators with native 4-bit support requires quantizing both weights and activations to realize the full throughput gains these formats provide. While post-training weight quantization has been extensively studied, activation quantization remains considerably more challenging and typically requires calibration data. In this work, we introduce DUALQUANT, a dual-scale, calibration-free post-training quantization framework that directly minimizes the weight-reconstruction Mean Squared Error (MSE) and, as an immediate by-product, yields per-channel activation rescalings pri

Read original source ↗ Open in workspace

recordType

paper

region

Global