Contents:

• 1. TorchServe
• 2. Troubleshooting Guide
• 3. Batch Inference with TorchServe
• 4. Code Coverage
• 5. Advanced configuration
• 6. Custom Service
• 7. TorchServe default inference handlers
• 8. Logging in Torchserve
• 9. TorchServe Metrics
• 10. Model Zoo
• 11. Request Envelopes
• 12. Running TorchServe
• 13. TorchServe model snapshot
• 14. TorchServe on Windows
• 15. TorchServe on Windows Subsystem for Linux (WSL)
• 16. Torchserve Use Cases
• 17. TorchServe Workflows

APIs

• TorchServe gRPC API
  • Python client example for gRPC APIs
• Inference API
  • API Description
  • Health check API
  • Predictions API
    • curl Example
  • curl Example
  • Explanations API
    • curl example
  • KFServing Inference API
    • curl example
  • KFServing Explanations API
    • curl example
• Management API
  • Register a model
    • Encrypted model serving
  • Scale workers
  • Describe model
  • Unregister a model
  • List models
  • API Description
  • Set Default Version
• Metrics API
  • Prometheus server
  • Grafana
• TorchServe REST API
• Workflow Inference API
  • Predictions API
    • curl Example
• Management API
  • Register a workflow
  • Describe workflow
  • Unregister a workflow
  • List workflows