gpu-mode/Triton-Puzzles

Puzzles for learning Triton

65
/ 100
Established

This project offers interactive puzzles to help deep learning practitioners learn Triton, an open-source language for programming AI accelerators. You'll solve challenges that involve memory operations, starting with simple examples and progressing to advanced algorithms like Flash Attention. This is for AI/ML engineers and researchers who want to optimize their models for GPUs using Triton.

2,338 stars. Actively maintained with 11 commits in the last 30 days.

Use this if you are an AI/ML engineer or researcher looking to learn how to program GPUs more efficiently using Triton.

Not ideal if you are a beginner programmer without prior experience in deep learning frameworks like PyTorch or NumPy, or if you only work with high-level AI libraries.

GPU programming AI model optimization deep learning engineering accelerator programming high-performance computing
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

2,338

Forks

207

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 18, 2026

Commits (30d)

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gpu-mode/Triton-Puzzles"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.