Quickstart
Start building awesome apps in under 5 minutes with solo server. This guide walks you through setting up your development environment, downloading your models and containers locally, and deploying them.
1. Installation Using pip
Solo Server is available as a Python package. Install it with:
Github Repo
GetSoloTech/solo-server
2. Set Up Your Solo Environment
Initialize your environment with:
This command guides you through the initial configuration, ensuring that your local environment is correctly set up for building and deploying your documentation.
3. Download Your First Model
Fetch your model huggingface identifier:
This step downloads your models locally at~/.cache/huggingface/hub using huggingface download cli interface.
4. Run Solo Server
Start the server for Hardware Aware Inference:
This command launches a local server (port athttp://localhost:5070) where you can view your models inference in real time. As you make changes to your model deployment, the server will automatically update the preview.