Shortcuts

TorchServe REST API

TorchServe use RESTful API for both inference and management calls. The API is compliance with OpenAPI specification 3.0. User can easily generate client side code for Java, Scala, C#, Javascript use swagger codegen.

When TorchServe startup, it start two web services:

By default, TorchServe listening on 8080 port for Inference API and 8081 on Management API. Both API is only accessible from localhost. Please see TorchServe Configuration for how to enable access from remote host.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources