llama.cpp Integrates Decision Models and /v1/systemone Endpoint for Local Inference

Core summary

One sentence to understand this update

llama.cpp now supports decision models via its new `/v1/systemone` endpoint, enabling local, efficient, and private Jev-style inference.

Impact & opportunity

What this could mean

Developers can now deploy decision-making capabilities locally with llama.cpp, facilitating private and efficient agentic applications.