InferAdmin is a lightweight management web interface for local LLM infrastructure. It provides a simple API for deploying and managing docker-based inference engines.
- Deploy and monitor docker based inference engines
- Deploy and monitor docker based web interfaces
- Manage GPU and storage resources
First git clone the repo, then use any of the following methods to install and run InferAdmin. Docker is the suggested way to run InferAdmin.
- Install Docker
- Install Nvidia Container Toolkit
- Run
docker compose up -d
- Run
uv run inferadmin