gpu-mode/Triton-Puzzles
Puzzles for learning Triton
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.
Stars
2,338
Forks
207
Language
Jupyter Notebook
License
Apache-2.0
Category
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.
Related frameworks
triton-inference-server/server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
hailo-ai/hailo_model_zoo
The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment
open-mmlab/mmdeploy
OpenMMLab Model Deployment Framework
hyperai/tvm-cn
TVM Documentation in Chinese Simplified / TVM 中文文档
triton-inference-server/model_analyzer
Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory...