Python package
max
The MAX Python API reference.
The MAX API provides a high-performance graph compiler and runtime library that executes AI models with incredible speed on a wide range of hardware.
MAX offers a layered architecture that lets you work at the level of abstraction that best fits your needs. From deploying production-ready models with a few lines of code to building custom neural networks from scratch, each layer builds upon the others so you can move between levels seamlessly as requirements evolve.
For an introduction, see the tutorial to get started with MAX graphs.
Packages and modules
diagnostics.gpu: GPU monitoring and performance diagnostics utilities.driver: Low-level device management and tensor operations.dtype: Unified data type system supporting various numeric formats.engine: Model execution runtime with automatic optimization.entrypoints: Command-line tools and serving infrastructure.experimental: Experimental features and APIs under active development.graph: Computational graph construction with 100+ operations for complete model control.interfaces: Universal interfaces for consistent API integration.kv_cache: KV cache management for efficient attention computation.nn: High-level neural network building blocks with automatic graph compilation.pipelines: Pre-built, optimized model architectures for immediate deployment.profiler: Performance profiling and tracing utilities.torch: PyTorch integration for custom operations and interoperability.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!