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 :doc:`installation instructions ` for your platform of choice. - Take a look at the :doc:`tutorials ` to learn how to write your first Triton program. .. toctree:: :maxdepth: 1 :caption: Getting Started :hidden: getting-started/installation getting-started/tutorials/index Python API ---------- - :doc:`triton ` - :doc:`triton.language ` - :doc:`triton.testing ` .. toctree:: :maxdepth: 1 :caption: Python API :hidden: python-api/triton python-api/triton.language python-api/triton.testing Triton MLIR Dialects and Ops -------------------- - :doc:`Triton MLIR Dialects and Ops ` .. toctree:: :maxdepth: 1 :caption: Triton MLIR Dialects :hidden: dialects/dialects Going Further ------------- Check out the following documents to learn more about Triton and how it compares against other DSLs for DNNs: - Chapter 1: :doc:`Introduction ` - Chapter 2: :doc:`Related Work ` .. toctree:: :maxdepth: 1 :caption: Programming Guide :hidden: programming-guide/chapter-1/introduction programming-guide/chapter-2/related-work .. _Triton: https://github.com/openai/triton