DEV Community

Cover image for Serving PyTorch Models in Production
Sangam SwadiK for Data Umbrella

Posted on

Serving PyTorch Models in Production

Summary posted by: Sangam SwadiK

Intro to serving models with PyTorch

Machine learning/Deep learning models are rarely deployed across the industry. The polls (Venturebeat, KdNuggets) indicate roughly 80-90 percent of the models developed never make it into production. This could be due to various reasons such as ROI, ineffective leadership, business needs or failure to incorporate MLOps.

As a Data Scientist/ML engineer, one of your responsibilities is to ensure a well designed and functional pipeline. And model deployment is an important part of the pipeline.

This is where the PyTorch ecosystem comes to rescue! PyTorch, TorchServe and many other projects built on PyTorch, can be used from model development until model deployment. There has also been an upward trend in PyTorch due to ease of usage.

Intro to Event

This talk is for a data scientist or ML engineer looking to serve their PyTorch models in production. It will cover post training steps that should be taken to optimize the model such as quantization and TorchScript. It will also walk the user in packaging and serving the model through Facebook's TorchServe.

Video

Resources

Section Timestamps of Video

About the Speakers

Bio

Nidhin Pattaniyil is a Machine Learning Engineer in Walmart Search.

Connect with the Speaker

Key Links

Top comments (0)