2比特量化新方法，让大模型推理更稳定高效
The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)
- 提出符号零三值量化（SZT），2比特实现确定性梯度更新
- 在固定资源下提升信息密度，优于非量化模型表现
- 适合追求高效推理的大模型部署场景
量化通常被视为以性能换计算资源的次优近似手段。然而，在固定总体资源预算下，这一视角将发生转变。本文提出符号零三值量化（Signed-Zero Ternary, SZT），一种2比特量化方法，可在无前向路径开销的前提下，确定性地提供梯度信息。分析表明，该方法可能在信息密度上优于非量化方案。
原文摘要 · Abstract (English)
Quantization is usually regarded as a means to trade quality of performance for reduced compute requirements, i.e., as a suboptimal approximation. However, if examined in terms of a fixed overall resource budget, a very different perspective arises. We introduce Signed-Zero Ternary (SZT), a 2-bit quantization that deterministically provides gradient information with no forward-path penalty. Our analysis provides evidence that it may improve information density compared to non-quantized alternatives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。