What exactly is a SavedModel, and how does TensorFlow Serving use it to run your model without your Python code?

A SavedModel contains saved_model.pb (the graph program including preprocessing ops that were traced), variables/ (checkpointed weights), assets/ (e.g., vocab files), and optionally a fingerprint. The key concept is signatures: named entry points (default 'serving_default') with typed tensor inputs/outputs, produced from @tf.function-traced functions. Because the graph is the program, TF Serving — a C++ binary — can execute it with zero Python dependencies. That's also why anything not traceable into the graph (Python-side feature fetching, dynamic control flow on Python objects) silently won't ship: it must either become TF ops inside the exported function or move to a pre-processing service. Serving conventions: models live at /models/<name>/<version>/ and the server hot-loads new integer versions, enabling atomic rollout/rollback by directory manipulation. Keras 3's model.export() (vs .save('.keras') for training checkpoints) is the current API for producing inference SavedModels.