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

Unified system for large-scale distributed training and inference.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)

Guidance language for controlling LLM generation with constraints, grammars, and JSON schemas.

Open SourceSelf HostedOffline
Intermediate
0.0 (0)

Library for easily accessing and processing ML datasets.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

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)

Gradient boosting library by Yandex with native categorical feature handling.

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