Portable Prediction Server¶
Availability information
The Portable Prediction Server is a premium feature exclusive to DatRobot MLOps. Contact your DataRobot representative or administrator for information on enabling this feature.
The Portable Prediction Server (PPS) is a remote DataRobot execution environment for DataRobot model packages (MLPKG files) distributed as a self-contained Docker image. It can host one or more production models. The models are accessible through DataRobot's Prediction API for predictions and Prediction Explanations.
| Topic | Describes |
|---|---|
| Portable Prediction Server | Downloading and configuring the Portable Prediction Server. |
| Portable Prediction Server running modes | Configuring the Portable Prediction Server for single-model or multi-model running mode. |
| Portable batch predictions | Scoring datasets in batches on a remote environment with the Portable Prediction Server. |
| Custom model Portable Prediction Server | Downloading and configuring the custom model Portable Prediction Server. |
CPU considerations
DataRobot strongly recommends using an Intel CPU to run the Portable Prediction Server. Using non-Intel CPUs can result in prediction inconsistencies, especially in deep learning models like those built with Tensorflow or Keras. This includes ARM architecture processors (e.g., AArch32 and AArch64).