// Build and deploy applications on inference.sh. Use when getting started, understanding the platform, or needing an overview of inference.sh development.
Configure inf.yml for inference.sh apps. Use when setting GPU, VRAM, RAM, categories, environment variables, packages.txt, or resource requirements.
Debug and troubleshoot inference.sh apps. Use when facing import errors, CUDA issues, memory problems, or deployment failures.
Handle graceful cancellation in inference.sh apps. Use when implementing long-running tasks that users might cancel.
Handle API keys and sensitive values in inference.sh apps. Use when adding secrets, accessing environment variables, or securing credentials.
Optimize inference.sh app performance. Use when handling memory, devices, model loading, mixed precision, or flash attention.
Track usage with output metadata in inference.sh apps. Use when implementing billing, counting tokens, or reporting image/video/audio generation metrics.
| name | building-inferencesh-apps |
| description | Build and deploy applications on inference.sh. Use when getting started, understanding the platform, or needing an overview of inference.sh development. |
Build and deploy applications on the inference.sh platform.
curl -fsSL https://cli.inference.sh | sh
infsh update # Update CLI
infsh login # Authenticate
infsh me # Check current user
infsh app init my-app # Create app
infsh app run # Test locally
infsh app deploy # Deploy
| Skill | Use When |
|---|---|
| using-the-cli | Running CLI commands for apps and agents |
| writing-app-logic | Creating inference.py |
| configuring-resources | Setting up inf.yml |
| managing-secrets | Handling API keys |
| using-oauth-integrations | Google Sheets, Drive |
| tracking-usage | Output metadata for billing |
| handling-cancellation | Long-running tasks |
| optimizing-performance | Best practices |
| debugging-issues | Troubleshooting |