{"ok":true,"entity":{"id":"llama-cpp","name":"llama.cpp","entityType":"product","officialName":"llama.cpp","canonicalName":"llama.cpp","displayName":"llama.cpp","category":"推論エンジン（OSS）","shortDescription":"C/C++で実装されたLLM推論エンジン。GGUF形式のモデルをGPUなしでもローカル環境で実行でき、オープンモデルをローカルで動かす基盤として広く使われる。","primaryCluster":"ai-open-model","parentEntity":null,"verificationStatus":"draft","website":"https://github.com/ggml-org/llama.cpp","updatedAt":"2026-07-18T11:08:14.467Z","secondaryClusters":["ai-infrastructure"],"alias":["llama cpp"],"searchKeywords":["ローカルLLM","GGUF","推論エンジン","量子化"]},"referenceIndex":["P-01-001","P-02-001","P-04-001","P-04-002","P-01-002","P-06-001"]}