PyTorch Inference Monitoring

See the Quick Start guide on how to install and configure Graphsignal.

Add the following code around inference. See API reference for full documentation.

with graphsignal.start_trace(endpoint='predict'):
    # function call or code segment

Examples

The PyTorch MNIST example illustrates where and how to add the start_trace method.

Model serving

Graphsignal provides a built-in support for server applications. See Model Serving guide for more information.

Useful links

• Performance Tuning Guide
• Accelerate PyTorch Model Inferencing