Inference
Also known as: model inference, serving
Running a trained model on new inputs to produce outputs - in production, inference economics (latency, throughput, cost) usually dominate architecture choices.
Also known as: model inference, serving
Running a trained model on new inputs to produce outputs - in production, inference economics (latency, throughput, cost) usually dominate architecture choices.
Contact if you need a term added for a security or procurement review.