MindControl - llama.cpp fork to guide the reasoning process via injection during sampling
Summary
MindControl is a fork of llama.cpp that allows guiding the reasoning process of language models through injection during sampling, enabling more controlled outputs.
Similar Articles
Benchmarked: MindControl for Llama.cpp
Benchmark results for MindControl, a sampler-level guided reasoning budget for llama.cpp, show multi-stage signaling reduces token consumption without accuracy loss, and sometimes improves it on easier tasks.
focus-llama: a llama.cpp fork implementing Declarative Attention (arXiv:2609.02737)
This article describes a fork of llama.cpp called focus-llama that implements Declarative Attention from a recent paper, allowing models to declare needed context chunks during inference to optimize KV cache usage and reduce decode time.
I used Anthropic's NLA to catch thoughts controlling Llama-70B's behavior that it couldn't see!
The author used Anthropic's Neural Linear Algebra (NLA) technique on Llama-70B to identify latent 'thoughts' (internal representations) that influence the model's behavior but are not directly visible to standard introspection, highlighting advances in mechanistic interpretability.
We really need llama.cpp to support changing thinking amount
The user advocates for llama.cpp to support adjustable thinking modes for AI models like Qwen 3.8 27b to enhance task-specific performance.
Ling 3.0 support merged into llama.cpp
Support for the new Ling 3.0 reasoning models has been integrated into llama.cpp, making them accessible via this development tool.