Model serving Archives

Building Flexible Ensemble ML Models with a Computational Graph

DoorDash extended its machine learning platform to support ensemble models.

Enabling Efficient Machine Learning Model Serving by Minimizing Network Overheads with gRPC

The challenge of building machine learning (ML)-powered applications is running inferences on large volumes of data and returning a prediction over the network within milliseconds, which can‚Äôt be done without minimizing network overheads.