Triton (OpenAI)

Language and compiler for writing GPU kernels in Python by OpenAI.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

Triton by OpenAI is a language and compiler for writing efficient GPU kernels in Python, letting researchers express custom CUDA-level operations without writing C++ or CUDA. It compiles tiled neural network primitives to fast GPU code and underpins optimizations such as FlashAttention. It aims for higher productivity than CUDA with more flexibility than fixed libraries. Released under the MIT license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Expert (5/5)
License
MIT
Minimum VRAM
8 GB
Added
Apr 3, 2026

Related Tools

JAX neural network library with PyTorch-like module system.

Open SourceSelf HostedOffline
Advanced
0.0 (0)

High-level deep learning API supporting JAX, TensorFlow, and PyTorch backends.

Open SourceSelf HostedOffline
Easy
0.0 (0)

Neural network library for JAX by Google providing Linen module system.

Open SourceSelf HostedOffline
Advanced
0.0 (0)

Deep learning platform by Baidu with industrial-strength deployment tools.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)
Featured

Hugging Face library for state-of-the-art NLP models

Open SourceSelf HostedOffline
Intermediate
0.0 (0)
Featured

End-to-end open-source ML platform by Google for training and deployment.

Open SourceSelf HostedOffline
Intermediate
0.0 (0)
Browse all AI Frameworks & Libraries tools