AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
This work addresses the challenge of memory-efficient deployment of LLMs for broader applications, presenting an incremental improvement in automated quantization methods.
The paper tackles the problem of deploying Large Language Models under strict memory constraints by developing AMQ, a framework for automated mixed-precision weight-only quantization that assigns layer-wise bit-widths to balance model quality and memory usage, achieving efficient exploration of over 10^{100} configurations to produce compact, high-performing models.
To enable broader deployment of Large Language Models (LLMs), it is essential to identify the best-performing model under strict memory constraints. We present AMQ, Automated Mixed-Precision Weight-Only Quantization, a framework that assigns layer-wise quantization bit-widths to optimally balance model quality and memory usage. However, the combinatorial search space, with over 10^{100} possible configurations, makes conventional black-box optimization infeasible. AMQ overcomes this challenge through four key innovations:(1) search space pruning using prior knowledge to exclude unpromising configurations, (2) quantization proxy to bypass costly format conversions during search, (3) quality predictor to minimize evaluation overhead, and (4) iterative search-and-update strategy for fast and stable convergence. By integrating these components, AMQ efficiently explores the quality-efficiency landscape, reaching the Pareto frontier and yielding LLMs that are both compact and high-performing. Our code is available at https://github.com/dlwns147/amq.