IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.

Skip to main content

For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python module

max.engine

Modular engine provides methods to load and execute AI models.

Model inference

`CompilationStopped`	Raised by `InferenceSession.compile()` when `pre_jit` stopped it.
`CompiledModel`	A compiled model artifact, ready for initialization with weights.
`CompileOnlyExecutionError`	A model compiled under virtual devices was asked to do something real.
`CompileOnlyModel`	Stands in for a `Model` compiled under virtual devices.
`InferenceSession`	Manages an inference session in which you can load and run models.
`Model`	A loaded model that you can execute.

Configuration

`DebugConfig`	Unified debug configuration for MAX inference.
`GPUProfilingMode`	alias of `Literal`['off', 'on', 'detailed']
`LogLevel`	Verbosity of Mojo logging in the compiled model.
`TensorSpec`	Defines the properties of a tensor, including its name, shape and data type.

Types

`CustomExtensionsType`	Represent a PEP 604 union type

Model inference
Configuration
Types