# Live Transformer Graphs: Running and Editing LLM Architectures on a Custom CUDA Engine

> Source: <https://discuss.huggingface.co/t/live-transformer-graphs-running-and-editing-llm-architectures-on-a-custom-cuda-engine/190915#post_1>
> Published: 2026-10-22 18:12:59+00:00

Has anyone ever wondered what it would be like to edit the model while its actually running live? well, this is the result… also note every part of the Kvcache persisted as state carries forever forward. This project is built into Leviathan which I have previously mentioned in Show/tell it’s all about manipulation of when a model is running live for the most part.