[Docx] add language (en/cn) switch links (#4470)

* add install docs

* 修改文档

* 修改文档
This commit is contained in:
yangjianfengo1
2025-10-17 15:47:41 +08:00
committed by GitHub
parent a3e0a15495
commit ba5c2b7e37
106 changed files with 206 additions and 0 deletions

View File

@@ -1,3 +1,5 @@
[English](../../quantization/wint2.md)
# WINT2量化
权重经过 [CCQ卷积编码量化](https://arxiv.org/pdf/2507.07145) 方法进行离线压缩。权重的实际存储数值类型为INT8每个INT8数值中打包了4个权重等价于每个权重2bits。激活不做量化。在推理过程中权重会被实时反量化并解码为BF16数值类型并使用BF16数值类型进行计算。