ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models
This work addresses the challenge of efficiently deploying LLMs on resource-constrained devices, representing an incremental improvement over existing quantization methods.
The paper tackles the problem of compressing large language models (LLMs) for reduced memory usage and improved latency by proposing ROSAQ, a rotation-based saliency-aware weight quantization method that identifies salient channels in a projected feature space and uses mixed-precision quantization, resulting in about 2.3x speedup over FP16 in token generation.
Quantization has been widely studied as an effective technique for reducing the memory requirement of large language models (LLMs), potentially improving the latency time as well. Utilizing the characteristic of rotational invariance of transformer, we propose the rotation-based saliency-aware weight quantization (ROSAQ), which identifies salient channels in the projection feature space, not in the original feature space, where the projected "principal" dimensions are naturally considered as "salient" features. The proposed ROSAQ consists of 1) PCA-based projection, which first performs principal component analysis (PCA) on a calibration set and transforms via the PCA projection, 2) Salient channel dentification, which selects dimensions corresponding to the K-largest eigenvalues as salient channels, and 3) Saliency-aware quantization with mixed-precision, which uses FP16 for salient dimensions and INT3/4 for other dimensions. Experiment results show that ROSAQ shows improvements over the baseline saliency-aware quantization on the original feature space and other existing quantization methods. With kernel fusion, ROSAQ presents about 2.3x speed up over FP16 implementation in generating 256 tokens with a batch size of 64.