GranQ: Efficient Channel-wise Quantization via Vectorized Pre-Scaling for Zero-Shot QAT
This addresses a computational bottleneck in neural network compression for scenarios with restricted data access, representing a strong specific gain.
The paper tackles the problem of activation distortion in zero-shot quantization under low-bit settings by proposing GranQ, an efficient pre-scaling strategy that eliminates runtime scaling overhead, achieving up to 5.45% higher accuracy on CIFAR-100 and surpassing full-precision baselines on CIFAR-10.
Zero-shot quantization (ZSQ) enables neural network compression without original training data, making it a promising solution for restricted data access scenarios. To compensate for the lack of data, recent ZSQ methods typically rely on synthetic inputs generated from the full-precision model. However, these synthetic inputs often lead to activation distortion, especially under low-bit settings. To mitigate this, existing methods typically employ per-channel scaling, but they still struggle due to the severe computational overhead during the accumulation process. To overcome this critical bottleneck, we propose GranQ, a novel activation quantization framework that introduces an efficient pre-scaling strategy. Unlike conventional channel-wise methods that repeatedly perform scaling operations during accumulation, GranQ applies scaling factors in a pre-scaling step through fully vectorized computation, eliminating runtime scaling overhead. This design enables GranQ to maintain fine-grained quantization accuracy while significantly reducing computational burden, particularly in low-bit quantization settings. Extensive experiments under quantization-aware training (QAT) settings demonstrate that GranQ consistently outperforms state-of-the-art ZSQ methods across CIFAR and ImageNet. In particular, our method achieves up to 5.45% higher accuracy in the 3-bit setting on CIFAR-100 and even surpasses the full-precision baseline on CIFAR-10.