AI 中文总结
本文提出开源可组合向量量化框架VQ-bench，整合7种量化原语实现25种量化器，提供统一开发与基准测试工具，助力向量量化领域研究与工程推进。
AI 中文摘要
向量量化是一个古老问题，但近来成为AI基础设施的核心，因此正迎来新一轮工程与研究活动的热潮。本文提供了用于开发和基准测试新量化算法的统一框架，描述了7种常见的概念量化原语，展示了如何任意组合它们，将25种常见量化器重新表达为这些原语的流水线，最后发布开源的VQ-bench以进一步扩展并公开可复现的基准测试。
英文摘要
Vector quantization is an old problem but has recently become central to AI infrastructure. It is therefore experiencing a surge of renewed engineering and research activity. This paper provides a unified framework for developing and benchmarking new quantization algorithms. We describe 7 common conceptual quantization primitives and show how to compose them arbitrarily. We then re-express 25 common quantizers as pipelines of these primitives. Finally, we publish VQ-bench as open-source to be extended further and make reproducible benchmarks publicly available.
CommentsResults available on www.vq-bench.com
