mlc-ai--mlc-llm/README.md

Note

本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。
English · 原始项目 · 上游 README
原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。

MLC LLM

基于 ML 编译的通用 LLM 部署引擎

入门 | 文档 | 博客

简介

MLC LLM 是一款面向大语言模型（LLM）的机器学习编译器与高性能部署引擎。本项目的使命是让每个人都能在自己的平台上原生开发、优化和部署 AI 模型。

	AMD GPU	NVIDIA GPU	Apple GPU	Intel GPU
Linux / Win	✅ Vulkan, ROCm	✅ Vulkan, CUDA	N/A	✅ Vulkan
macOS	✅ Metal (dGPU)	N/A	✅ Metal	✅ Metal (iGPU)
Web Browser	✅ WebGPU and WASM
iOS / iPadOS	✅ Metal on Apple A-series GPU
Android	✅ OpenCL on Adreno GPU		✅ OpenCL on Mali GPU

MLC LLM 在 MLCEngine 上编译并运行代码——这是一款跨上述平台的统一高性能 LLM 推理引擎。MLCEngine 提供与 OpenAI 兼容的 API（OpenAI-compatible API），可通过 REST 服务器、Python、JavaScript、iOS、Android 使用，均由同一套引擎与编译器支撑，我们正与社区持续改进。

入门

请访问我们的文档以开始使用 MLC LLM。

• 安装
• 快速入门
• 简介

引用

如果您觉得本项目有用，请考虑引用我们的工作：

@software{mlc-llm,
    author = {{MLC team}},
    title = {{MLC-LLM}},
    url = {https://github.com/mlc-ai/mlc-llm},
    year = {2023-2025}
}

MLC LLM 的底层技术包括：

参考文献（点击展开）

@inproceedings{tensorir,
    author = {Feng, Siyuan and Hou, Bohan and Jin, Hongyi and Lin, Wuwei and Shao, Junru and Lai, Ruihang and Ye, Zihao and Zheng, Lianmin and Yu, Cody Hao and Yu, Yong and Chen, Tianqi},
    title = {TensorIR: An Abstraction for Automatic Tensorized Program Optimization},
    year = {2023},
    isbn = {9781450399166},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3575693.3576933},
    doi = {10.1145/3575693.3576933},
    booktitle = {Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2},
    pages = {804–817},
    numpages = {14},
    keywords = {Tensor Computation, Machine Learning Compiler, Deep Neural Network},
    location = {Vancouver, BC, Canada},
    series = {ASPLOS 2023}
}

@inproceedings{metaschedule,
    author = {Shao, Junru and Zhou, Xiyou and Feng, Siyuan and Hou, Bohan and Lai, Ruihang and Jin, Hongyi and Lin, Wuwei and Masuda, Masahiro and Yu, Cody Hao and Chen, Tianqi},
    booktitle = {Advances in Neural Information Processing Systems},
    editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
    pages = {35783--35796},
    publisher = {Curran Associates, Inc.},
    title = {Tensor Program Optimization with Probabilistic Programs},
    url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/e894eafae43e68b4c8dfdacf742bcbf3-Paper-Conference.pdf},
    volume = {35},
    year = {2022}
}

@inproceedings{tvm,
    author = {Tianqi Chen and Thierry Moreau and Ziheng Jiang and Lianmin Zheng and Eddie Yan and Haichen Shen and Meghan Cowan and Leyuan Wang and Yuwei Hu and Luis Ceze and Carlos Guestrin and Arvind Krishnamurthy},
    title = {{TVM}: An Automated {End-to-End} Optimizing Compiler for Deep Learning},
    booktitle = {13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)},
    year = {2018},
    isbn = {978-1-939133-08-3},
    address = {Carlsbad, CA},
    pages = {578--594},
    url = {https://www.usenix.org/conference/osdi18/presentation/chen},
    publisher = {USENIX Association},
    month = oct,
}