{"type": "article", "title": "C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/c-2-kv-compressed-and-composable-kv-cache-reuse-for-efficient-llm-inference", "original_source": "https://www.machinebrief.com/news/cdollar2dollarkv-compressed-and-composable-kv-cache-reuse-fo-pwdj", "published": "2026-07-21T04:00:00+00:00", "accessed": "2026-07-22", "id": "c-2-kv-compressed-and-composable-kv-cache-reuse-for-efficient-llm-inference"}