focus-llama: a llama.cpp fork implementing Declarative Attention (arXiv:2609.02737)
英文标题：focus-llama: a llama.cpp fork implementing Declarative Attention (arXiv:2609.02737)
I forked llama.cpp to implement Declarative Attention (arXiv:2609.02737, Google DeepMind and KAIST AI). The model declares in its own output which context chunks it needs <focus magic\_chunks="N">), and the engine listens and restricts what the following tokens can attend to. No scorer, no training:
打开原文相关 2 · 机会 0
中文
I forked llama.cpp to implement Declarative Attention (arXiv:2609.02737, Google DeepMind and KAIST AI). The model declares in its own output which context chunks it needs <focus magic\_chunks="N">), and the engine listens and restricts what the following tokens can attend to. No scorer, no training:
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
I forked llama.cpp to implement Declarative Attention (arXiv:2609.02737, Google DeepMind and KAIST AI). The model declares in its own output which context chunks it needs <focus magic\_chunks="N">), and the engine listens and restricts what the following tokens can attend to. No scorer, no training: