---
id: 20261120-T0-09
title: "QDA：用智能体闭环设计大模型量化方案"
title_en: "QDA: Closed-Loop LLM Quantization Design with Agents"
url: https://ai.daily.yangsir.net/daily/20261120-T0-09
issue_date: 2026-11-20
publish_date: 2026-11-19T05:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2611.23388
---

# QDA：用智能体闭环设计大模型量化方案

训练后量化是低成本部署大模型的标准手段，但最优量化配方因模型和精度而异，每来一个新模型专家都得重新设计，耗时且依赖经验。研究者提出QDA，用智能体构建闭环量化设计流程，自动为不同模型和精度搜索合适的量化方案。这减少了人工调参的重复劳动，有望让量化部署更快适配新模型，对需要控制推理成本的工程团队有实际意义。

## English Version

**QDA: Closed-Loop LLM Quantization Design with Agents**

Post-training quantization is the standard way to serve large language models at low cost, but the best recipe varies across models and precisions, forcing experts to redesign it for every new model. QDA builds a closed-loop quantization design process with agents that automatically searches suitable recipes for different models and precisions. The approach reduces repetitive manual tuning and could let quantized deployment adapt to new models faster, with practical value for engineering teams managing inference costs.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2611.23388)

**详情页**：https://ai.daily.yangsir.net/daily/20261120-T0-09

---

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