---
id: 20260606-T0-06
title: "LiftQuant：连续位宽LLM量化方案"
title_en: "LiftQuant: Continuous Bit-Width LLM Quantization"
url: https://ai.daily.yangsir.net/daily/20260606-T0-06
issue_date: 2026-06-06
publish_date: 2026-06-05T04:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2606.04050
---

# LiftQuant：连续位宽LLM量化方案

arXiv提出LiftQuant，解决LLM量化中的'部署鸿沟'。传统量化方法受限于整数位宽（如2/3位），无法灵活适配不同内存预算。该方法通过维度提升和投影技术实现连续位宽量化，让模型能更精确地匹配硬件资源，提升部署效率。

## English Version

**LiftQuant: Continuous Bit-Width LLM Quantization**

arXiv paper proposes LiftQuant to solve the 'deployment gap' in LLM quantization. Traditional methods are limited to rigid integer bit-widths, preventing optimal fitting to memory budgets. This approach uses dimensional lifting and projection for continuous bit-width quantization, enabling better hardware resource matching and deployment efficiency.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2606.04050)

**详情页**：https://ai.daily.yangsir.net/daily/20260606-T0-06

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*