经 AI Skill Hub 精选评估,高精度低位LLM推理工具 获评「推荐使用」。已获得 1.4k 颗 GitHub Star,这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
A SOTA量化算法,实现高精度低位LLM推理,提高推理效率,降低推理成本。
高精度低位LLM推理工具 是一款基于 Python 开发的开源工具,专注于 quantization、LLM、inference 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
A SOTA量化算法,实现高精度低位LLM推理,提高推理效率,降低推理成本。
高精度低位LLM推理工具 是一款基于 Python 开发的开源工具,专注于 quantization、LLM、inference 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install auto-round
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install auto-round
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/intel/auto-round
cd auto-round
pip install -e .
# 验证安装
python -c "import auto_round; print('安装成功')"
# 命令行使用
auto-round --help
# 基本用法
auto-round input_file -o output_file
# Python 代码中调用
import auto_round
# 示例
result = auto_round.process("input")
print(result)
# auto-round 配置文件示例(config.yml) app: name: "auto-round" debug: false log_level: "INFO" # 运行时指定配置文件 auto-round --config config.yml # 或通过环境变量配置 export AUTO_ROUND_API_KEY="your-key" export AUTO_ROUND_OUTPUT_DIR="./output"
<p align="center"> <img src="docs/imgs/AutoRound.png" alt="AutoRound Overview" width="20%"> </p>
<a href="https://huggingface.co/Intel"> <img alt="Model Checkpoints" src="https://img.shields.io/badge/%F0%9F%A4%97%20HF-Models-F57C00"> </a>
English | 简体中文
User Guide | 用户指南
--- <div align="left">
auto-round-rtn will now default to using the model-free approach: Doc.auto-round-rtn --scheme FP8_BLOCK.enable_alg_ext and use the AutoScheme API for mixed-precision quantization to reproduce the results: Paper, Notes for evaluating LLaMA models.--enable_alg_ext: Accuracy.--enable_alg_ext: Accuracy✅ Superior Accuracy Delivers strong performance even at 2–3 bits example models, with leading results at 4 bits benchmark.
✅ Ecosystem Integration Seamlessly works with Transformers, vLLM, SGLang and more.
✅ Multiple Formats Export Support AutoRound, AutoAWQ, AutoGPTQ, and GGUF for maximum compatibility. Details are shown in export formats
✅ Fast Mixed Bits/Dtypes Scheme Generation Automatically configure in minutes, with about 1.1X-1.5X the model’s BF16 RAM size as overhead. Accuracy results and user guide.
✅ Optimized Round-to-Nearest Mode Use --iters 0 for fast quantization with some accuracy drop for 4 bits. Details are shown in opt_rtn mode
✅ Affordable Quantization Cost Quantize 7B models in about 10 minutes on a single GPU. Details are shown in quantization costs
✅ 10+ VLMs Support Out-of-the-box quantization for 10+ vision-language models example models, support matrix
✅ Multiple Recipes Choose from auto-round-best, auto-round, and auto-round-light to suit your needs. Details are shown in quantization recipes
✅ Advanced Utilities Includes multiple gpus quantization, multiple calibration datasets and support for 10+ runtime backends.
✅ Beyond weight only quantization. We are actively expanding support for additional datatypes such as MXFP, NVFP, W8A8, and more.
AutoScheme provides an automatic algorithm to generate adaptive mixed bits/data-type quantization recipes. Please refer to the user guide for more details on AutoScheme. ~~~python from auto_round import AutoRound, AutoScheme
model_name = "Qwen/Qwen3-8B" avg_bits = 3.0 scheme = AutoScheme(avg_bits=avg_bits, options=("GGUF:Q2_K_S", "GGUF:Q4_K_S"), ignore_scale_zp_bits=True) layer_config = {"lm_head": "GGUF:Q6_K"}
```bash
pip install auto-round-hpu
The full list of supported arguments is provided by calling auto-round -h on the terminal.
ModelScope is supported for model downloads, simply set AR_USE_MODELSCOPE=1.
auto-round \
--model Qwen/Qwen3-0.6B \
--scheme "W4A16" \
--format "auto_round" \
--output_dir ./tmp_autoround
We offer another two recipes, auto-round-best and auto-round-light, designed for optimal accuracy and improved speed, respectively. Details are as follows. <details> <summary>Other Recipes</summary>
```bash
auto-round-best \ --model Qwen/Qwen3-0.6B \ --scheme "W4A16" \ --low_gpu_mem_usage
bash
```python from auto_round import AutoRound
<details> <summary>Click to expand</summary>
This feature is experimental and may be subject to changes.
By default, AutoRound only quantize the text module of VLMs and uses NeelNanda/pile-10k for calibration. To quantize the entire model, you can enable quant_nontext_module by setting it to True, though support for this feature is limited. For more information, please refer to the AutoRound readme.
```python from auto_round import AutoRound
auto-round是一款开源的高精度低位LLM推理工具,提供了SOTA量化算法,实现高精度低位LLM推理,提高推理效率,降低推理成本。工具易于安装和使用,适合于LLM推理场景。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:高精度低位LLM推理工具 的核心功能完整,质量良好。对于AI 技术爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | auto-round |
| 原始描述 | 开源AI工具:A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessl。⭐1.4k · Python |
| Topics | quantizationLLMinference |
| GitHub | https://github.com/intel/auto-round |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-25 · 更新时间:2026-05-25 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。