In a move that will be welcomed by developers, Oracle today open-sourced ‘Graphpipe’, a tool created to make it easy to serve Machine Learning (ML) models in the Cloud. It’s available on GitHub now.
Graphpipe has been made by popular frameworks like TensorFlow, MXNet, Caffe2, & PyTorch, & was designed to simplify the deployment of ML for use on mobile apps and IoT devices, as well as Web services for end users or AI for internal use at companies. It is a standard protocol now. Oracle had developed this to provide it to a wider audience of ML.
Use of the tool may mean developers don’t have to build custom APIs to deploy AI models or be concerned about which popular framework was used to create a model. It provides a standard, high-performance protocol for transmitting tensor data over the network, along with simple implementations of clients & servers that make deploying & querying machine learning models from any framework very easy.
Image Credit: Oracle
