For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Python function
max_compile
max_compile()
max.pipelines.diffusion.max_compile(compile_target: Callable[[...], Any] | Module[..., Any], input_types: Iterable[TensorType] | None = None) → CompileWrapper
max.pipelines.diffusion.max_compile(compile_target: None = None, input_types: Iterable[TensorType] | None = None) → Callable[[Callable[[...], Any] | Module[..., Any]], CompileWrapper]
Decorator or function to compile a target with specified input types.
-
Parameters:
-
- compile_target – The function or module to compile. If None, returns a decorator.
- input_types – The input types for the compilation.
-
Returns:
-
A CompileWrapper instance if compile_target is provided, otherwise a decorator.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!