{"type":"link","version":"1.0","title":"Treating KV cache as hierarchical memory eliminates streaming video re-encoding: 10× faster TTFT, 68% fewer tokens","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/kv-cache-as-hierarchical-memory-10x-ttft","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}