Interactive Jacobian-Lens visualizer and live steerer for GGUF models on llama.cpp
Summary
An interactive Jacobian-lens visualizer and live steerer for GGUF models running on llama.cpp, enabling real-time model interpretability and control.
Similar Articles
PSA: unsloth/GLM-5.2-GGUF is uploading
unsloth has uploaded a GGUF version of GLM-5.2 to Hugging Face, providing ready-to-use model files for various inference engines like llama.cpp, vLLM, and SGLang.
model: Granite4 Vision by gabe-l-hart · Pull Request #23545 · ggml-org/llama.cpp
This pull request adds support for the Granite4 Vision model to llama.cpp, an open-source LLM inference engine.
I kept rewriting parameters every time I swapped models on vLLM and llama.cpp, so I built a tool to manage them (llmux, MIT)
A developer built llmux, an open-source tool to simplify managing model profiles across different engines like vLLM and llama.cpp, allowing one-click switching with Docker and NVIDIA GPU support.
whats happening on llama.cpp
A significant update to llama.cpp requires all previously generated GGUF files to be regenerated, indicating a major breaking change to the model format.
I built a tiny proxy that gives GLM 5.2 vision (or any text LLM) – MIT
VisionBridge is an open-source proxy that gives text-only LLMs vision capabilities by letting a reasoning model query a separate vision model for image inspection, OCR, and more.