Announcing VisLlama - a UI for engines

[Data Sculpting]

Hi all, sharing that I published a fairly robust UI wrapper for inference engines on Windows & Linux, initial support is llama.cpp (including via Docker) and Strata - adding new engines should be as simple as a JSON definition (next phase is engine expansion) - the UI already supports just about everything needed.

https://github.com/DataSculpting/VisLlama

It's not just a UI, it allows juggling of multiple engine build presets, multiple model presets, allows everything manageable via UI, GPU assignment including priority and typical splits, auto-launch, launch order. It's everything LM Studio or Ollama should be but aren't. It also puts ALL loaded models (regardless of engine) behind a common OpenAI-compatible endpoint and has separate router management options. Built-in chat, system stats, historical inference stats, etc.