[{"data":1,"prerenderedAt":120},["ShallowReactive",2],{"licenses-commercially-usable-ai":3},{"vllm":4,"ollama":59,"koboldcpp":92},{"id":5,"slug":5,"name":6,"url":7,"curatedDescription":8,"category":9,"section":14,"repo":18,"media":50,"source":53,"sync":57},"vllm","vLLM","https://github.com/vllm-project/vllm","State-of-the-art serving engine with PagedAttention and continuous batching. Currently the fastest production-grade LLM server.",{"id":10,"slug":10,"title":11,"navTitle":12,"order":13},"inference-engines-and-serving","Inference Engines & Serving","Serving",3,{"id":15,"slug":15,"title":16,"order":17},"high-performance-serving-and-api-servers","High-performance Serving & API Servers",2,{"host":19,"owner":20,"name":5,"fullName":21,"stars":22,"license":23,"primaryLanguage":24,"homepage":25,"topics":26,"description":47,"pushedAt":48,"archived":49,"fork":49},"github","vllm-project","vllm-project/vllm",81935,"Apache-2.0","Python","https://vllm.ai",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"amd","blackwell","cuda","deepseek","deepseek-v3","gpt","gpt-oss","inference","kimi","llama","llm","llm-serving","model-serving","moe","openai","pytorch","qwen","qwen3","tpu","transformer","A high-throughput and memory-efficient inference and serving engine for LLMs","2026-06-04T18:01:24Z",false,{"iconUrl":51,"avatarUrl":52},null,"https://avatars.githubusercontent.com/u/136984999?v=4",{"readmeUrl":54,"readmeLine":55,"sourceHash":56},"https://github.com/alvinreal/awesome-opensource-ai/blob/main/README.md",286,"fb157d63a81e09435737672cb2c10cb3ef440c1b9be35512bd9443bd8cb68959",{"lastSyncedAt":58},"2026-07-12T12:00:53.360Z",{"id":60,"slug":60,"name":61,"url":62,"curatedDescription":63,"category":64,"section":65,"repo":69,"media":87,"source":89,"sync":91},"ollama","Ollama","https://github.com/ollama/ollama","Dead-simple local LLM runner with a one-line install, model registry, and OpenAI-compatible API.",{"id":10,"slug":10,"title":11,"navTitle":12,"order":13},{"id":66,"slug":66,"title":67,"order":68},"local-on-device-inference","Local / On-device Inference",1,{"host":19,"owner":60,"name":60,"fullName":70,"stars":71,"license":72,"primaryLanguage":73,"homepage":74,"topics":75,"description":85,"pushedAt":86,"archived":49,"fork":49},"ollama/ollama",173169,"MIT","Go","https://ollama.com",[30,76,77,78,79,80,33,36,81,37,82,83,84,60,43],"gemma","gemma3","glm","go","golang","llama3","llms","minimax","mistral","Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.","2026-06-04T18:05:37Z",{"iconUrl":51,"avatarUrl":88},"https://avatars.githubusercontent.com/u/151674099?v=4",{"readmeUrl":54,"readmeLine":90,"sourceHash":56},269,{"lastSyncedAt":58},{"id":93,"slug":93,"name":94,"url":95,"curatedDescription":96,"category":97,"section":98,"repo":99,"media":115,"source":117,"sync":119},"koboldcpp","KoboldCpp","https://github.com/LostRuins/koboldcpp","User-friendly llama.cpp fork focused on role-playing and creative writing.",{"id":10,"slug":10,"title":11,"navTitle":12,"order":13},{"id":66,"slug":66,"title":67,"order":68},{"host":19,"owner":100,"name":93,"fullName":101,"stars":102,"license":103,"primaryLanguage":104,"homepage":105,"topics":106,"description":112,"pushedAt":113,"archived":49,"fork":114},"LostRuins","LostRuins/koboldcpp",10703,"AGPL-3.0","C++","https://github.com/LostRuins/koboldcpp/releases/latest",[76,107,108,109,93,110,36,111,37,84],"ggml","gguf","koboldai","language-model","llamacpp","Run GGUF models easily with a KoboldAI UI. One File. Zero Install.","2026-06-04T17:40:10Z",true,{"iconUrl":51,"avatarUrl":116},"https://avatars.githubusercontent.com/u/39025047?v=4",{"readmeUrl":54,"readmeLine":118,"sourceHash":56},275,{"lastSyncedAt":58},1783865043227]