[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-local-inference":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"9b51ed95-0c58-4c86-8ed4-f5e0cd8b8df9","local inference","local-inference",0,null,[11,20,27],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"8a164bd6-6f92-47a6-87fb-72a6371aae17","why-llama-cpp-should-treat-turboquant-as-default-en","Why llama.cpp should treat TurboQuant as the new default path","TurboQuant is the right direction for llama.cpp because asymmetric KV compression cuts memory without breaking compatibility.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779481556833-a9v3.png","en","2026-05-22T20:25:23.12744+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"5ed4267c-b54b-4c73-8192-79bfacaf438d","llama-cpp-local-llm-inference-cpp-en","llama.cpp adds local LLM inference in C\u002FC++","ggml-org’s llama.cpp keeps expanding local LLM support with OpenAI-compatible serving, browser WebGPU, and broad hardware backends.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779480952129-tpau.png","2026-05-22T20:15:28.848286+00:00",{"id":28,"slug":29,"title":30,"summary":31,"category":16,"image_url":32,"cover_image":32,"language":18,"created_at":33},"f915d006-a80b-435e-a93c-a9a0b30dbd17","singnova-h-studio-local-ai-pc-risc-v-en","SingNova-H Studio turns local AI into a PC","SingNova-H Studio packs 200 TOPS into a local AI PC built around RISC-V dataflow design.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779362176673-nfm3.png","2026-05-21T11:15:54.577829+00:00"]