Foundations of Large Language Model Compression -- Part 1: Weight Quantization
This addresses the need to reduce computational costs and environmental impact for deploying LLMs, though it appears incremental as it builds on existing quantization methods with a new optimization perspective.
The paper tackles the problem of compressing large language models (LLMs) for deployment on resource-constrained devices by proposing a quantization technique based on convex optimization, which scales to models with hundreds of billions of parameters and allows flexible compression to any specified size post-training.
In recent years, compression of large language models (LLMs) has emerged as an important problem to enable language model deployment on resource-constrained devices, reduce computational costs, and mitigate the environmental footprint of large-scale AI infrastructure. In this paper, we lay down the foundation for LLM quantization from a convex optimization perspective and propose a quantization technique that builds on this foundation for optimum quantization outcomes. Our quantization framework, CVXQ, scales to models containing hundreds of billions of weight parameters and provides users with the flexibility to compress models to any specified model size, post-training. A reference implementation of CVXQ can be obtained from github.com/seannz/cvxq.