[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2362":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":34,"discoverSource":35},2362,"mlc-llm","mlc-ai\u002Fmlc-llm","mlc-ai","Universal LLM Deployment Engine with ML Compilation","https:\u002F\u002Fllm.mlc.ai\u002F",null,"Python",22787,2066,193,286,0,2,33,168,17,44.95,"Apache License 2.0",false,"main",true,[27,28,29,30],"language-model","llm","machine-learning-compilation","tvm","2026-06-12 02:00:40","\u003Cdiv align=\"center\">\n\n# MLC LLM\n\n[![Installation](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-latest-green)](https:\u002F\u002Fllm.mlc.ai\u002Fdocs\u002F)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-apache_2-blue)](https:\u002F\u002Fgithub.com\u002Fmlc-ai\u002Fmlc-llm\u002Fblob\u002Fmain\u002FLICENSE)\n[![Join Discoard](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FJoin-Discord-7289DA?logo=discord&logoColor=white)](https:\u002F\u002Fdiscord.gg\u002F9Xpy2HGBuD)\n[![Related Repository: WebLLM](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRelated_Repo-WebLLM-fafbfc?logo=github)](https:\u002F\u002Fgithub.com\u002Fmlc-ai\u002Fweb-llm\u002F)\n\n**Universal LLM Deployment Engine with ML Compilation**\n\n[Get Started](https:\u002F\u002Fllm.mlc.ai\u002Fdocs\u002Fget_started\u002Fquick_start) | [Documentation](https:\u002F\u002Fllm.mlc.ai\u002Fdocs) | [Blog](https:\u002F\u002Fblog.mlc.ai\u002F)\n\n\u003C\u002Fdiv>\n\n## About\n\nMLC LLM is a machine learning compiler and high-performance deployment engine for large language models.  The mission of this project is to enable everyone to develop, optimize, and deploy AI models natively on everyone's platforms. \n\n\u003Cdiv align=\"center\">\n\u003Ctable style=\"width:100%\">\n  \u003Cthead>\n    \u003Ctr>\n      \u003Cth style=\"width:15%\"> \u003C\u002Fth>\n      \u003Cth style=\"width:20%\">AMD GPU\u003C\u002Fth>\n      \u003Cth style=\"width:20%\">NVIDIA GPU\u003C\u002Fth>\n      \u003Cth style=\"width:20%\">Apple GPU\u003C\u002Fth>\n      \u003Cth style=\"width:24%\">Intel GPU\u003C\u002Fth>\n    \u003C\u002Ftr>\n  \u003C\u002Fthead>\n  \u003Ctbody>\n    \u003Ctr>\n      \u003Ctd>Linux \u002F Win\u003C\u002Ftd>\n      \u003Ctd>✅ Vulkan, ROCm\u003C\u002Ftd>\n      \u003Ctd>✅ Vulkan, CUDA\u003C\u002Ftd>\n      \u003Ctd>N\u002FA\u003C\u002Ftd>\n      \u003Ctd>✅ Vulkan\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>macOS\u003C\u002Ftd>\n      \u003Ctd>✅ Metal (dGPU)\u003C\u002Ftd>\n      \u003Ctd>N\u002FA\u003C\u002Ftd>\n      \u003Ctd>✅ Metal\u003C\u002Ftd>\n      \u003Ctd>✅ Metal (iGPU)\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>Web Browser\u003C\u002Ftd>\n      \u003Ctd colspan=4>✅ WebGPU and WASM \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>iOS \u002F iPadOS\u003C\u002Ftd>\n      \u003Ctd colspan=4>✅ Metal on Apple A-series GPU\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd>Android\u003C\u002Ftd>\n      \u003Ctd colspan=2>✅ OpenCL on Adreno GPU\u003C\u002Ftd>\n      \u003Ctd colspan=2>✅ OpenCL on Mali GPU\u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftbody>\n\u003C\u002Ftable>\n\u003C\u002Fdiv>\n\nMLC LLM compiles and runs code on MLCEngine -- a unified high-performance LLM inference engine across the above platforms. MLCEngine provides OpenAI-compatible API available through REST server, python, javascript, iOS, Android, all backed by the same engine and compiler that we keep improving with the community.\n\n## Get Started\n\nPlease visit our [documentation](https:\u002F\u002Fllm.mlc.ai\u002Fdocs\u002F) to get started with MLC LLM.\n- [Installation](https:\u002F\u002Fllm.mlc.ai\u002Fdocs\u002Finstall\u002Fmlc_llm)\n- [Quick start](https:\u002F\u002Fllm.mlc.ai\u002Fdocs\u002Fget_started\u002Fquick_start)\n- [Introduction](https:\u002F\u002Fllm.mlc.ai\u002Fdocs\u002Fget_started\u002Fintroduction)\n\n## Citation\n\nPlease consider citing our project if you find it useful:\n\n```bibtex\n@software{mlc-llm,\n    author = {{MLC team}},\n    title = {{MLC-LLM}},\n    url = {https:\u002F\u002Fgithub.com\u002Fmlc-ai\u002Fmlc-llm},\n    year = {2023-2025}\n}\n```\n\nThe underlying techniques of MLC LLM include:\n\n\u003Cdetails>\n  \u003Csummary>References (Click to expand)\u003C\u002Fsummary>\n\n  ```bibtex\n  @inproceedings{tensorir,\n      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},\n      title = {TensorIR: An Abstraction for Automatic Tensorized Program Optimization},\n      year = {2023},\n      isbn = {9781450399166},\n      publisher = {Association for Computing Machinery},\n      address = {New York, NY, USA},\n      url = {https:\u002F\u002Fdoi.org\u002F10.1145\u002F3575693.3576933},\n      doi = {10.1145\u002F3575693.3576933},\n      booktitle = {Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2},\n      pages = {804–817},\n      numpages = {14},\n      keywords = {Tensor Computation, Machine Learning Compiler, Deep Neural Network},\n      location = {Vancouver, BC, Canada},\n      series = {ASPLOS 2023}\n  }\n\n  @inproceedings{metaschedule,\n      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},\n      booktitle = {Advances in Neural Information Processing Systems},\n      editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},\n      pages = {35783--35796},\n      publisher = {Curran Associates, Inc.},\n      title = {Tensor Program Optimization with Probabilistic Programs},\n      url = {https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2022\u002Ffile\u002Fe894eafae43e68b4c8dfdacf742bcbf3-Paper-Conference.pdf},\n      volume = {35},\n      year = {2022}\n  }\n\n  @inproceedings{tvm,\n      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},\n      title = {{TVM}: An Automated {End-to-End} Optimizing Compiler for Deep Learning},\n      booktitle = {13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)},\n      year = {2018},\n      isbn = {978-1-939133-08-3},\n      address = {Carlsbad, CA},\n      pages = {578--594},\n      url = {https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fosdi18\u002Fpresentation\u002Fchen},\n      publisher = {USENIX Association},\n      month = oct,\n  }\n  ```\n\u003C\u002Fdetails>\n","MLC LLM 是一个用于大型语言模型的机器学习编译器和高性能部署引擎。该项目的核心功能包括通过 ML 编译技术优化 AI 模型，并在多种平台上实现高效推理，支持 AMD GPU、NVIDIA GPU、Apple GPU 以及 Intel GPU 等不同硬件环境下的部署。它提供了一个统一的高性能LLM推理引擎MLCEngine，该引擎兼容OpenAI API，并可通过REST服务器、Python、JavaScript、iOS及Android等多种方式进行访问。MLC LLM特别适合需要跨平台快速部署和运行大型语言模型的应用场景，如开发基于Web或移动设备的智能应用。","2026-06-11 02:49:39","top_language"]