[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-edge-ai-inference":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"7bafddbd-9174-4ae9-a5fe-805b5e28f41f","edge AI inference","edge-ai-inference",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"cbaeb6db-c465-4659-b35b-640435c673bf","why-kv-cache-compression-will-decide-edge-ai-inference-en","Why KV-cache compression will decide edge AI inference","TurboQuant-style KV-cache compression is the real bottleneck-breaker for edge AI inference.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779285828871-4n8z.png","en","2026-05-20T14:03:20.811149+00:00"]