Welcome to Triton’s documentation!

Triton is a language and compiler for parallel programming. It aims to provide a Python-based programming environment for productively writing custom DNN compute kernels capable of running at maximal throughput on modern GPU hardware.

Getting Started

• Follow the installation instructions for your platform of choice.

• Take a look at the tutorials to learn how to write your first Triton program.

Triton API

• triton

• triton.language

• triton.testing

• Triton semantics

• triton.language.extra.cuda

Gluon

• Learn about Gluon’s lower-level programming model in the Gluon overview.

• Browse the Gluon tutorials, examples, and API reference.

Triton MLIR Dialects and Ops

• Triton MLIR Dialects and Ops

Going Further

Check out the following documents to learn more about Triton and how it compares against other DSLs for DNNs:

• Chapter 1: Introduction

• Chapter 2: Related Work

• Chapter 3: Debugging