Triton Resources
This page serves as a reference for useful Triton resources. Triton is a language and compiler for parallel programming that provides a Python-based programming environment for writing custom DNN compute kernels capable of running at maximal throughput on modern GPU hardware.
What is Triton?
Triton is a language and compiler for parallel programming that 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.
Python-Based Programming
Write custom DNN compute kernels in Python with a familiar programming environment.
Maximal Throughput
Achieve optimal performance on modern GPU hardware with compiler optimizations.
Parallel Programming
Language and compiler designed specifically for parallel computing workloads.
Open Source
MIT licensed with an active community of contributors and users.
Official Resources
Official Documentation
Complete documentation for the Triton language and compiler, including tutorials, API reference, and programming guides.
Key Features:
- Getting Started Guide
- Python API Reference
- Triton MLIR Dialects
- Programming Tutorials
GitHub Repository
Official development repository for the Triton language and compiler. Access source code, issues, and contribute to the project.
Key Features:
- 15.8k+ Stars
- Active Development
- MIT License
- Community Contributions
Official YouTube Channel
Official YouTube channel featuring tutorials, talks, and updates about Triton development and usage.
Key Features:
- Video Tutorials
- Technical Talks
- Latest Updates
- Community Content
Learn Triton
LeetGPU
Interactive platform for learning GPU programming with Triton. Practice writing and optimizing GPU kernels through hands-on exercises and challenges.
Triton Tutorial Series
Comprehensive video tutorial series covering Triton fundamentals, advanced concepts, and practical examples for GPU programming.
Kernelize & Triton
Kernelize builds on the open-source Triton compiler to provide AI inference systems for AI inference accelerators. Our platform leverages Triton's powerful capabilities to auto-generate optimized backends for a wide variety of hardware targets, helping developers write high-performance GPU kernels in Python once and deploy them across GPUs, NPUs, TPUs, and more.