Getting Started

Get your first model deployed on SEDI in under 5 minutes.

1. Install the CLI

npm install -g sedi-cli

2. Authenticate

sedi login

This will open your browser to authorize the CLI. You can also generate an API token from your dashboard.

3. Deploy your model

sedi deploy model.gguf

SEDI will automatically detect the model format, optimize for inference, and provision GPU resources. Your model will be available at a *.yourdomain.app endpoint.

4. Configure your endpoint

sedi endpoint set max-tokens=4096 temperature=0.7

Set context windows, temperature, max tokens, and guardrails. Every endpoint gets automatic TLS, rate limiting, and usage tracking.

Quick tip

Enable automatic model redeployments by connecting your HuggingFace account in the dashboard. Every push to your model repository triggers a new deployment.