{"data":{"slug":"liguodongiot-llm-action","name":"llm-action","tagline":"Aims to share large model technology principles and practical experience (large model engineering, application implementation)","github_url":"https://github.com/liguodongiot/llm-action","owner":"liguodongiot","repo":"llm-action","owner_avatar_url":"https://avatars.githubusercontent.com/u/13220186?v=4","primary_language":"HTML","stars":24898,"forks":2842,"topics":["llm","llm-inference","llm-serving","llm-training","llmops"],"archived":false,"github_pushed_at":"2026-07-19T13:13:31+00:00","maintenance_label":"Active","stars_delta_30d":162,"url":"https://www.graphcanon.com/tools/liguodongiot-llm-action","markdown_url":"https://www.graphcanon.com/tools/liguodongiot-llm-action.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/liguodongiot-llm-action","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=liguodongiot-llm-action","description":"本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）","homepage_url":"https://www.zhihu.com/column/c_1456193767213043713","license":"Apache-2.0","open_issues":19,"watchers":200,"ai_summary":"Repository focused on the sharing of knowledge regarding large language models including their engineering, practical deployment, inference, serving, and training.","readme_excerpt":"

\n \n

\n\n\n

\n\n \n \n \n \n \n \n

\n\n\n## 目录\n\n- :snail: [LLM训练](#llm训练)\n - 🐫 [LLM训练实战](#llm训练实战)\n - 🐼 [LLM参数高效微调技术原理](#llm微调技术原理)\n - 🐰 [LLM参数高效微调技术实战](#llm微调实战)\n - 🐘 [LLM分布式训练并行技术](#llm分布式训练并行技术)\n - 🌋 [分布式AI框架](#分布式ai框架)\n - 📡 [分布式训练网络通信](#分布式训练网络通信)\n - :herb: [LLM训练优化技术](#llm训练优化技术)\n - :hourglass: [LLM对齐技术](#llm对齐技术)\n- 🐎 [LLM推理](#llm推理)\n - 🚀 [LLM推理框架](#llm推理框架)\n - ✈️ [LLM推理优化技术](#llm推理优化技术)\n- ♻️ [LLM压缩](#llm压缩)\n - 📐 [LLM量化](#llm量化)\n - 🔰 [LLM剪枝](#llm剪枝)\n - 💹 [LLM知识蒸馏](#llm知识蒸馏)\n - ♑️ [低秩分解](#低秩分解)\n- :herb: [LLM测评](#llm测评)\n - 🔯 [LLM效果评测](#llm效果评测)\n - 🔘 [LLM推理性能压测](#llm推理性能压测)\n- :palm_tree: [LLM数据工程](#llm数据工程)\n - :dolphin: [LLM微调高效数据筛选技术](#llm微调高效数据筛选技术)\n- :cyclone: [提示工程](#提示工程)\n- ♍️ [LLM算法架构](#llm算法架构)\n- :jigsaw: [LLM应用开发](#llm应用开发)\n- 🀄️ [LLM国产化适配](#llm国产化适配)\n- 🔯 [AI编译器](#ai编译器)\n- 🔘 [AI基础设施](#ai基础设施)\n - :maple_leaf: [AI加速卡](#ai加速卡)\n - :octocat: [AI集群网络通信](#ai集群网络通信)\n- 💟 [LLMOps](#llmops)\n- 🍄 [LLM生态相关技术](#llm生态相关技术)\n- 💹 [LLM性能分析](#llm性能分析)\n- :dizzy: [LLM面试题](#llm面试题)\n- 🔨 [服务器基础环境安装及常用工具](#服务器基础环境安装及常用工具)\n- 💬 [LLM学习交流群](#llm学习交流群)\n- 👥 [微信公众号](#微信公众号)\n- ⭐️ [Star History](#star-history)\n- :link: [AI工程化课程推荐](#ai工程化课程推荐)\n\n\n## LLM训练\n\n### LLM训练实战\n\n下面汇总了我在大模型实践中训练相关的所有教程。从6B到65B，从全量微调到高效微调（LoRA，QLoRA，P-Tuning v2），再到RLHF（基于人工反馈的强化学习）。\n\n| LLM | 预训练/SFT/RLHF... | 参数 | 教程 | 代码 |\n| --------------------------- | ----------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------- |\n| Alpaca | full fine-turning | 7B | [从0到1复现斯坦福羊驼（Stanford Alpaca 7B）](https://zhuanlan.zhihu.com/p/618321077) | [配套代码](https://github.com/liguodongiot/llm-action/tree/main/llm-train/alpaca) |\n| Alpaca(LLaMA) | LoRA | 7B~65B | 1.[足够惊艳，使用Alpaca-Lora基于LLaMA(7B)二十分钟完成微调，效果比肩斯坦福羊驼](https://zhuanlan.zhihu.com/p/619426866)
2. [使用 LoRA 技术对 LLaMA 65B 大模型进行微调及推理](https://zhuanlan.zhihu.com/p/632492604) | [配套代码](https://github.com/liguodongiot/llm-action/tree/main/llm-train/alpaca-lora) |\n| BELLE(LLaMA/Bloom) | full fine-turning | 7B | 1.[基于LLaMA-7B/Bloomz-7B1-mt复现开源中文对话大模型BELLE及GPTQ量化](https://zhuanlan.zhihu.com/p/618876472)
2. [BELLE(LLaMA-7B/Bloomz-7B1-mt)大模型使用GPTQ量化后推理性能测试](https://zhua","github_created_at":"2023-05-23T05:29:16+00:00","created_at":"2026-07-07T17:32:47.504271+00:00","updated_at":"2026-08-16T18:02:10.724395+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"deployment","name":"deployment"},{"slug":"engineering","name":"engineering"},{"slug":"inference","name":"inference"},{"slug":"large-model","name":"large model"},{"slug":"training","name":"training"}],"trust":{"provenance":{"is_fork":false,"github_id":644235905,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T18:02:10.025Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":28,"last_release_at":null,"stars_delta_30d":162,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:59:35.281Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-16T18:02:10.452Z"},"languages":{"value":["html"],"source":"github.language","observed_at":"2026-08-16T18:02:10.452Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-16T18:02:10.452Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{},"constraints":null,"when_to_use":["- When you need detailed examples and best practices of implementing large language models (LLMs) in real-world applications, llm-action provides insights into the challenges faced during LLM's actual","- You require information specifically about deploying and managing large model operations using a framework dedicated to comprehensive coverage of various phases from training to serving."],"when_not_to_use":["- If your focus is narrowly on cutting-edge research rather than practical implementation details, llm-action may not be the best resource as it focuses more on deployment processes.","- When looking for a full-stack solution that includes detailed code implementations and libraries for each phase (training, serving), llm-action might fall short. It shines in sharing knowledge but不如"],"source":"enrich:decision_facts","observed_at":"2026-07-11T13:44:37.841Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"llm-action aims to share large model technology principles and practical experiences covering areas such as engineering, deployment, inference, serving, and training."},{"label":"License detail","value":"llm-action is open-source under the Apache-2.0 license."}]}}