Introducing Triton: Open-source GPU programming for neural networks

OpenAI Blog2021-07-28 15:000 views

We’re releasing Triton 1.0, an open-source Python-like programming language which enables researchers with no CUDA experience to write highly efficient GPU code—most of the time on par with what an expert would be able to produce.

Source：https://openai.com/index/triton

My favorites

PreviousOpenAI Codex NextEvaluating large language models trained on code

Margo Engine: a small WebGPU engine with a Rust/Wasm core (Apache-2.0, not on npm yet)

I have made Margo Engine public. It is a small WebGPU engine for the web, with a Rust kernel compiled to Wasm. Repo: Git

0Rust Users Forum

As Test Takers Turn to AI for Answers, Exam Security Must Catch Up

It's hard to detect whether someone is using artificial intelligence (AI) to cheat on IT certification exams, but new to

0Dark Reading

Get Started With Meta Muse in Python: Spark and Glimmer

Getting started with Meta Muse in Python takes only a few lines of code, because Meta’s Model API speaks the same protoc

0Real Python

Anthropic and Google Make Their Best AI Models Cheaper

Real Python AI News · Weekly edition · The week of November 7–13, 2026 Stop Falling Behind on AI. Catch Up in Five Minut

0Real Python

Claude’s Duet agent is a little neurotic and surprisingly helpful

Let’s get to work. | Photo: Allison Johnson / The Verge Normally, the products I test don't offer to help me write up my

0The Verge

Surviving a transient outage without locking out paying customers: grace windows over signed cached validation

An online license check buys you things an offline one cannot: live seat counts, instant revocation, usage metering. But

0dev.to