TorchServe

TorchServe is a flexible and easy to use tool for serving PyTorch models.

A quick overview and examples for both serving and packaging are provided below. Detailed documentation and examples are provided in the docs folder.

Install TorchServe

Core APIs

• Inference API
• TorchServe default inference handlers
• Logging on Torchserve
• Pre-requisites
• Types of logs
• Modifying the behavior of the logs
• Enable asynchronous logging
• Management API
• Metrics on TorchServe
• TorchServe REST API
• Advanced configuration

TorchServe Usage

• Running the TorchServe
• Batch Inference with TorchServe
• Custom Service