{"data":{"slug":"liguodongiot-llm-resource","name":"llm-resource","tagline":"LLM全栈优质资源汇总","github_url":"https://github.com/liguodongiot/llm-resource","owner":"liguodongiot","repo":"llm-resource","owner_avatar_url":"https://avatars.githubusercontent.com/u/13220186?v=4","primary_language":"Shell","stars":725,"forks":85,"topics":["llm","llmops"],"archived":false,"github_pushed_at":"2025-07-15T16:52:24+00:00","maintenance_label":"Dormant","stars_delta_30d":2,"url":"https://www.graphcanon.com/tools/liguodongiot-llm-resource","markdown_url":"https://www.graphcanon.com/tools/liguodongiot-llm-resource.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/liguodongiot-llm-resource","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=liguodongiot-llm-resource","description":"LLM全栈优质资源汇总","homepage_url":null,"license":"Apache-2.0","open_issues":0,"watchers":6,"ai_summary":"A comprehensive collection of high-quality resources related to Large Language Models (LLMs)","readme_excerpt":"# llm-resource（LLM 百宝箱）\n\nLLM全栈优质资源汇总\n\n> 非常欢迎大家也参与进来，收集更多优质大模型相关资源。\n\n## 目录\n\n- 🐼 [LLM算法](#llm算法)\n- 🐘 [LLM训练](#llm训练)\n\t- 🐘 [LLM微调](#llm微调)\n\t- 🐼 [LLM对齐](#llm对齐)\n- 🔥 [LLM推理](#llm推理)\n- :palm_tree: [LLM数据工程（Data Engineering）](#llm数据工程)\n- 📡 [LLM压缩](#llm压缩)\n- 🐰 [LLM测评](#llm测评)\n- 🐘 [AI基础知识](#ai基础知识)\n- 📡 [AI基础设施](#ai基础设施)\n\t- :palm_tree: [AI芯片](#ai芯片)\n\t- 🐰 [CUDA](#cuda)\n- 🐘 [AI编译器](#ai编译器)\n- 🐰 [AI框架](#ai框架)\n- 📡 [LLM应用开发](#llm应用开发)\n- 🐘 [LLMOps](#llmops)\n- 📡 [LLM实践](llm实践)\n- 📡[微信公众号文章集锦](#微信公众号文章集锦)\n\n\n\n## LLM算法\n\n\n### Transformer\n\n原理：\n- [Transformer模型详解（图解最完整版](https://zhuanlan.zhihu.com/p/338817680)\n- [OpenAI ChatGPT（一）：十分钟读懂 Transformer](https://zhuanlan.zhihu.com/p/600773858)\n- [Transformer的结构是什么样的？各个子模块各有什么作用？](https://blog.csdn.net/m0_54929869/article/details/118881804)\n- [以Transformer结构为基础的大模型参数量、计算量、中间激活以及KV cache剖析](https://mp.weixin.qq.com/s/3JYz6yrLeBr5ujip3LZe6w)\n- [Transformer 一起动手编码学原理](https://mp.weixin.qq.com/s/NgUNuWhvp2SqG-XWYv2PGQ)\n- [为什么transformer(Bert)的多头注意力要对每一个head进行降维？](http://www.sniper97.cn/index.php/note/deep-learning/note-deep-learning/4002/)\n- [Decoder-Only Transformers: The Workhorse of Generative LLMs](https://cameronrwolfe.substack.com/p/decoder-only-transformers-the-workhorse)\n\n\n源码：\n\n- [OpenAI ChatGPT（一）：Tensorflow实现Transformer](https://zhuanlan.zhihu.com/p/603243890)\n- [OpenAI ChatGPT（一）：十分钟读懂 Transformer](https://zhuanlan.zhihu.com/p/600773858)\n- [GPT （一）transformer原理和代码详解](https://zhuanlan.zhihu.com/p/632880248)\n- [Transformer源码详解（Pytorch版本）](https://zhuanlan.zhihu.com/p/398039366)\n- [搞懂Transformer结构，看这篇PyTorch实现就够了](https://zhuanlan.zhihu.com/p/339207092)\n\n\n\n### GPT1\n\n\n### GPT2\n\n\n- GPT2 源码：https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt2/modeling_gpt2.py\n- GPT2 源码解析：https://zhuanlan.zhihu.com/p/630970209\n- nanoGPT：https://github.com/karpathy/nanoGPT/blob/master/model.py\n\n\n- 7.3 GPT2模型深度解析：http://121.199.45.168:13013/7_3.html\n- GPT（三）GPT2原理和代码详解: https://zhuanlan.zhihu.com/p/637782385\n- GPT2参数量剖析: https://zhuanlan.zhihu.com/p/640501114\n\n\n### ChatGPT\n\n- [State of GPT：大神Andrej揭秘OpenAI大模型原理和训练过程](https://mp.weixin.qq.com/s/zmEGzm1cdXupNoqZ65h7yg)\n- [OpenAI联合创始人亲自上场科普GPT，让技术小白也能理解最强AI](https://mp.weixin.qq.com/s/MD4WwwJLXm8rEm-sniX8Gw)\n\n\n\n\n\n### GLM\n\n- [预训练语言模型：GLM](https://zhuanlan.zhihu.com/p/641499380)\n\n\n### LLaMA\n\n\n\n### MOE 大模型\n\n- [Mixtral-8x7B MoE大模型微调实践，超越Llama2-65B](https://mp.weixin.qq.com/s?__biz=MzU3Mzg5ODgxMg==&mid=2247486657&idx=1&sn=c5a5e55b01243f477d063c9194d24f42&chksm=fd3be592ca4c6c84bf5eefff23dcc38eeb83624e9f53bbd9a72afba71e235dddf814549322ba&token=499509118&lang=zh_CN#rd)\n- [大模型分布式训练并行技术（八）-MOE并行](https://mp.weixin.qq.com/s?__biz=MzU3Mzg5ODgxMg==&mid=2247486145&idx=1&sn=299c28153b286465be26e18153c6db5d&chksm=fd3be392ca4c6a84be283dad80f584443302ea29fc95744f83727e7d9d68952d3a0f8b1b66d5&token=499509118&lang=zh_CN#rd)\n- [MoE架构模型爆发或将带飞国产AI芯片](https://mp.weixin.qq.com/s?__biz=MzU3Mzg5ODgxMg==&mid=2247488422&idx=1&sn=eeb18ec0f5b9e972df31d65e7db13f8f&chksm=fd3bfaf5ca4c73e38a696fe7b6f33a30af962fdddfabd92d74b1d06190442759aabe7b560f22&token=499509118&lang=zh_CN#rd)\n- [大模型的模型融合方法概述](https://mp.weixin.qq.com/s?__biz=MzU3Mzg5ODgxMg==&mid=2247487652&idx=1&sn=1bbf692b6e1dc6bae719c8e0a10293a0&chksm=fd3bf9f7ca4c70e16473a98d5408f6daea5e8c116a88cb3f41dfb00ffb7f6016874ee092224c&token=499509118&lang=zh_CN#rd)\n- [混合专家模型 (MoE) 详解](https://zhuanlan.zhihu.com/p/674698482)\n- [群魔乱舞：MoE大模型详解](https://zhuanlan.zhihu.com/p/677638939)\n- [大模型LLM之混合专家模型MoE（上-基础篇）](https://zhuanlan.zhihu.com/p/672712751)\n- [大模型LLM之混合专家模型MoE（下-实现篇）](https://zhuanlan.zhihu.com/p/673048264)\n\n\n### 下一代大模型\n\n- https://github.com/NExT-GPT/NExT-GPT\n- https://next-gpt.github.io/\n- [Introduction to NExT-GPT: Any-to-Any Multimodal Large Language Model](https://www.kdnuggets.com/introduction-to-nextgpt-anytoany-multimodal-large-language-model)\n\n\n\n### 多模态大模型\n\nA Survey on Multimodal Large Language Models：https://arxiv.org/pdf/2306.13549\nEfficient-Multimodal-LLMs-Survey：https://github.com/lijiannuist/Efficient-","github_created_at":"2023-08-27T11:45:51+00:00","created_at":"2026-07-07T17:43:18.134383+00:00","updated_at":"2026-08-21T00:01:20.338752+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"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"}],"tags":[{"slug":"llm","name":"llm"},{"slug":"llmops","name":"llmops"}],"trust":{"provenance":{"is_fork":false,"github_id":683688484,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-21T00:01:19.579Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":401,"last_release_at":null,"stars_delta_30d":2,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:23:23.452Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-21T00:01:20.049Z"},"languages":{"value":["shell"],"source":"github.language","observed_at":"2026-08-21T00:01:20.049Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-21T00:01:20.049Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["需要全面的LLM资源时，如开发、研究或学习大型语言模型框架","寻找Shell脚本相关的LLM工具和实例"],"when_not_to_use":["寻求针对特定框架（非全栈）的深入细节和支持时","如果项目严格要求使用专有许可证工具而非Apache-2.0许可工具时"],"source":"enrich:decision_facts","observed_at":"2026-07-12T17:20:43.167Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"LLM全栈优质资源汇总 - 高质量的大语言模型相关资源集合"}]}}