llama.cpp b12059 optimizes unified KV cache for multi-sequence

How it developed

1. November 3, 2026llama.cpp ReleasesWhere it started

   llama.cpp b12059 optimizes unified KV cache for multi-sequence

2. November 7, 2026llama.cpp Releases

   llama.cpp adds Kimi K3.1-Pro support

   llama.cpp adds Kimi K3.1-Pro support using DSA and linear-attention KDA layers