Glossary term
Glossary term
Infrastructure and Serving
A platform to deploy trained models in production.
Created for this library
An ML platform team uses TensorFlow Serving to expose production models behind stable APIs with versioned endpoints.
A search-quality team uses TensorFlow Serving for low-latency online inference on its ranker.
A startup deploys its production model with TensorFlow Serving in Kubernetes so it can scale horizontally with traffic.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License