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).
Mojo package
kernels
High-performance compute kernels, operators, and tensor APIs for MAX graphs.
The MAX AI kernels library provides the building blocks for AI inference and other compute-intensive workloads on CPU and GPU, including linear algebra functions like matrix multiplication, neural network operators such as attention and convolution, quantization routines, key-value caches for transformer models, and primitives for multi-GPU communication and extending a MAX graph with custom operations.
Packages
-
algorithm: Free-form row-wise reduction library: theReduceOpmonoid trait, therowwisescaffolder (Row/reduce/map/emit), and the Row-based pure reductions used by the graph reduction kernels. -
builtin_kernels: Provides the graph compiler's built-in kernel registrations. -
comm: Provides communication primitives for multi-GPU workloads. -
extensibility: Surface needed to write GraphCompiler kernel entry points. -
kv_cache: Contains implementations for several types of key-value caches. -
linalg: Provides CPU and GPU implementations of linear algebra functions. -
nn: Provides neural network operators for deep learning models. -
pipeline: Generic compile-time software pipelining for GPU kernels: schedule generation and verification. -
profiling_range: Provides Mojo wrappers for MAX's libkineto-backed range profiler. -
quantization: This package contains a set of APIs for quantizing tensor data. -
shmem: Implements a subset of OpenSHMEM for multi-node GPU communication. -
state_space: State space model kernels for Mamba and related architectures. -
structured_kernels: Shared GPU kernel primitives for structured kernel architectures.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!