Online Inference
The model is temporarily fixed; predictions are immediate.
What must be fast
Feature lookup, preprocessing parity, model execution and response serialization.
Typical stack
Feast/Redis · KServe/Triton/BentoML · XGBoost/ONNX/PyTorch.
Examples
Fraud, product ranking, credit scoring and image inference.
request → online_features(entity_id, event_time) → model.predict(feature_vector) → log(prediction_id, feature_version, model_version)