NVIDIA/accelerated-computing-hub

NVIDIA curated collection of educational resources related to general purpose GPU programming.

What it solves

This project provides a centralized, open-access repository for learning materials focused on GPU computing. It addresses the need for accessible, up-to-date documentation, tutorials, and best practices to help developers master accelerated computing techniques.

How it works

The hub offers a collection of interactive tutorials and guides that can be run directly on platforms like NVIDIA Brev or Google Colab. Each tutorial includes configuration files, such as Docker Compose, to help users quickly set up the necessary environment and hardware requirements to execute the code examples.

Who it’s for

It is designed for learners, developers, and researchers interested in GPU computing, ranging from those just starting with CUDA to those looking for advanced optimization techniques and deployment practices.

Highlights

  • A wide range of topics including CUDA C++, Accelerated Python, Standard Parallelism, and NVIDIA Warp.
  • Interactive syllabi and notebooks ranging from short 2-hour sessions to comprehensive 2-day courses.
  • Ready-to-use Docker Compose files for easy environment deployment.
  • Clear guidance on hardware requirements for different tutorials, such as specific GPU types and driver versions.
  • Open-source code examples licensed under Apache 2.0, with documentation available under Creative Commons.

Related

  • Project
    MiniMax-AI/minimax-code

    MiniMax Code (CLI `mcode`) is an AI‑driven coding assistant that lets you describe code changes in natural language, then automatically edits, tests, and runs the code in your local project. It works with MiniMax’s own model or any OpenAI/Anthropic‑compatible endpoint, offers interactive TUI, headless scripting, and a desktop UI, and includes a browser‑based demo (pocket‑pet) that shows the full prompt‑to‑working‑app loop.

  • Project
    trailofbits/claude-code-config

    A collection of opinionated configurations, sandboxing rules, and hooks for Claude Code to enable secure, high-throughput autonomous AI coding.

  • Project
    Emanuele-web04/synara

    A local-first desktop workspace that centralizes the management, execution, and review of multiple AI coding agents and their associated tasks.

  • Project
    google/gin-config

    Gin is a lightweight dependency injection framework for Python that simplifies configuration management by allowing function and class parameters to be set via external files.