{"type": "article", "title": "Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/recent-developments-in-llm-architectures-kv-sharing-mhc-and-compressed-attention", "original_source": "https://magazine.sebastianraschka.com/p/recent-developments-in-llm-architectures", "published": "2026-05-16T11:33:51+00:00", "accessed": "2026-07-09", "id": "recent-developments-in-llm-architectures-kv-sharing-mhc-and-compressed-attention"}