MAX Engine
MAX Engine incorporates best-in-class compiler and runtime technologies to create the world's fastest and most extensible unified inference engine.
An introduction to the features and technology in MAX Engine.Get started with MAX Engine
MAX Engine intro
Model inference
A walkthrough of the MAX Engine Python API, showing how to load and run a model. A walkthrough of the C API, showing how to load and run a trained model. A walkthrough of the Mojo MAX Engine API, showing how to load and run a model.Run inference with Python
Run inference with C
Run inference with Mojo
Model optimization
Learn how to run MLPerf benchmark scenarios from the command line. Learn how to visualize your model in Netron as a MAX Engine graphBenchmark a model
Visualize a model
Model building
Learn how to build a high-performance graph for MAX Engine.Build a model with MAX Graph API
References
The MAX Engine Python API reference. The root package for the Mojo MAX Engine APIs The MAX Engine C API reference. CLI interface to MAX Engine.MAX Engine Python API
MAX Engine Mojo API
MAX Engine C API
max