2021-03-05 22:49:39 -05:00
Welcome to Triton's documentation!
==================================
2021-03-06 17:35:11 -05:00
Triton is an imperative language and compiler for parallel programming. It aims to provide a programming environment for productively writing custom DNN compute kernels capable of running at maximal throughput on modern GPU hardware.
2021-03-05 22:49:39 -05:00
2021-03-06 17:35:11 -05:00
Getting Started
---------------
- Follow the :doc:`installation instructions <getting-started/installation>` for your platform of choice.
- Take a look at the :doc:`tutorials <getting-started/tutorials/index>` to learn how to write your first Triton program.
2021-03-05 22:49:39 -05:00
.. toctree::
:maxdepth: 1
2021-03-06 17:35:11 -05:00
:caption: Getting Started
:hidden:
getting-started/installation
2021-03-19 16:19:37 -04:00
getting-started/tutorials/index
2021-04-21 01:40:29 -04:00
Language Reference
-------------------
- Checkout the :doc:`Python API Documentation <language-reference/python-api/index>`
.. toctree::
:maxdepth: 1
:caption: Language Reference
:hidden:
language-reference/python-api/index
Going Further
2021-03-23 17:10:07 -04:00
------------------
2021-03-19 16:19:37 -04:00
Check out the following documents to learn more about Triton and how it compares against other DSLs for DNNs:
2021-03-23 17:10:07 -04:00
- Chapter 1: :doc:`Introduction <programming-guide/chapter-1/introduction>`
- Chapter 2: :doc:`Related Work <programming-guide/chapter-2/related-work>`
2021-03-19 16:19:37 -04:00
.. toctree::
:maxdepth: 1
:caption: Programming Guide
:hidden:
2021-03-23 17:10:07 -04:00
programming-guide/chapter-1/introduction
2021-04-21 01:40:29 -04:00
programming-guide/chapter-2/related-work
