Batch Prediction On New Data With Preprocessing Reuse And Output Formatting

A low-code framework for building custom AI models like LLMs and other deep neural networks. [#opensource](https://github.com/ludwig-ai/ludwig)

Unique: Automatically reuses the fitted preprocessor from training during inference, ensuring preprocessing consistency without requiring users to manually apply the same transformations, and handles batching and output formatting transparently

vs others: More convenient than manual preprocessing + model inference because preprocessing is automatic and consistent, yet less flexible than custom inference code because output formatting and preprocessing cannot be modified at inference time