Ray : for building distributed applications.

#ray #api #huggingface

I have started looking at Ray serve and hugging face. Ray serve is helpful in deploying AI and ML models on the cloud and the in house servers. You can expose api to Ray serve very easily. You can build AI & ML apps with Ray serve. It has the following features :

Providing simple primitives for building and running distributed applications.
Enabling end users to parallelize single machine code, with little to zero code changes.
Including a large ecosystem of applications, libraries, and tools on top of the core Ray to enable complex applications.