RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm
This addresses efficiency challenges for deploying large language models in resource-constrained environments, representing an incremental improvement over existing quantization methods.
The paper tackles the problem of post-training quantization for large language models, which often requires heavy calibration data and inflexible bit choices, by proposing RaanA, a framework that achieves competitive performance with state-of-the-art methods while being fast, requiring minimal calibration data, and enabling flexible bit allocation.
Post-training Quantization (PTQ) has become a widely used technique for improving inference efficiency of large language models (LLMs). However, existing PTQ methods generally suffer from crucial limitations such as heavy calibration data requirements and inflexible choice of target number of bits. In this paper, we propose RaanA, a unified PTQ framework that overcomes these challenges by introducing two novel components: 1) RaBitQ-H, a variant of a randomized vector quantization method RaBitQ, designed for fast, accurate, and highly efficient quantization; and 2) AllocateBits, an algorithm that optimally allocates bit-widths across layers based on their quantization sensitivity. RaanA achieves competitive performance with state-of-the-art quantization methods while being extremely fast, requiring minimal calibration data, and enabling flexible bit allocation. Extensive experiments demonstrate RaanA's efficacy in balancing efficiency and accuracy. The code is publicly available at https://github.com/FFTYYY/RaanA .