PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Add clear entry for leaderboard (#2500)
Wenhua Cheng523251eba8a3
diff --git a/README.md b/README.mdindex 3e7e95219..e2c6af825 100644--- a/README.md+++ b/README.md@@ -18,9 +18,15 @@</a><a href="https://pepy.tech/projects/auto-round" style="text-decoration:none;"><img src="https://static.pepy.tech/badge/auto-round" alt="PyPI Downloads"></a>- English | [简体中文](README_CN.md)+<p align="center">+<a href="https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard" style="text-decoration:none;">+<img alt="Quantize Your Model for Free" src="https://img.shields.io/badge/%F0%9F%91%89%20%E5%85%8D%E8%B4%B9%E9%87%8F%E5%8C%96%E6%82%A8%E7%9A%84%E6%A8%A1%E5%9E%8B%20%7C%20Quantize%20Your%20Model%20for%20FREE-2E7D32?style=for-the-badge">+</a>+</p>++ [简体中文](README_CN.md) | English-[User Guide](./docs/step_by_step.md) | [用户指南](./docs/step_by_step_CN.md) +[用户指南](./docs/step_by_step_CN.md) | [User Guide](./docs/step_by_step.md) ---<div align="left">@@ -31,7 +37,6 @@ AutoRound is an easy-to-use post-training quantization toolkit for Large LanguagIt supports several practical low-bit and adaptive-bit quantization algorithms, with a particular focus on [SignRoundV1](https://arxiv.org/pdf/2309.05516) and [SignRoundV2](http://arxiv.org/abs/2512.04746).AutoRound is designed to deliver strong accuracy at ultra-low bit widths while keeping quantization costs reasonable. It supports widely used data types and quantization schemes, including WNA16, MXFP4, NVFP4, and FP8, as well as low-bit model formats such as GGUF.It integrates with popular ecosystems including Transformers, vLLM, and SGLang, and supports deployment across Intel CPUs and XPUs, Gaudi accelerators, and NVIDIA GPUs.-For usage details, please refer to the [User Guide](./docs/step_by_step.md).<p align="center">diff --git a/README_CN.md b/README_CN.mdindex 897820d32..10d7638ad 100644--- a/README_CN.md+++ b/README_CN.md@@ -18,9 +18,15 @@</a><a href="https://pepy.tech/projects/auto-round" style="text-decoration:none;"><img src="https://static.pepy.tech/badge/auto-round" alt="PyPI Downloads"></a>- [English](README.md) | 简体中文+<p align="center">+<a href="https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard" style="text-decoration:none;">+<img alt="免费量化您的模型" src="https://img.shields.io/badge/%F0%9F%91%89%20%E5%85%8D%E8%B4%B9%E9%87%8F%E5%8C%96%E6%82%A8%E7%9A%84%E6%A8%A1%E5%9E%8B%20%7C%20Quantize%20Your%20Model%20for%20FREE-2E7D32?style=for-the-badge">+</a>+</p>++ 简体中文 | [English](README.md)-[User Guide](./docs/step_by_step.md) | [用户指南](./docs/step_by_step_CN.md) +[用户指南](./docs/step_by_step_CN.md) | [User Guide](./docs/step_by_step.md) ---<div align="left">