CUDA Python: Performance meets Productivity

The Modular Platform (includes MAX & Mojo)

Diagram as Code Tool Written in Rust with Draggable Editing

LinkedIn scraper to retrieve and store a live stream of job postings

Foundation Model for Physics Simulations

Fast and memory-efficient exact attention

Mamba SSM architecture

A tiny vLLM-inspired optimized inference server.

Code for the 9/6 Hackathon

How to ensure correctness and ship LLM generated kernels in PyTorch

1st Place Team Crane: @aswinkumar1999 @rathull @kyolebu

1st place. Team Crane's solution the 9/6 Jane Street x GPU_MODE hackaton! @aswinkumar1999 @rathull @kyolebu

Buttercup finds and patches software vulnerabilities

Competitive GPU kernel optimization platform.

A SCIP indexer for Ruby, powered by Sorbet

SCIP indexer for the C# programming language. Built with the Roslyn .NET compiler

An updated adaption of the Keras2Cpp library designed for use in C1Games' Terminal AI competition.

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Transformers on Meta's emg2qwerty surface electromyographic (sEMG) touch typing dataset. Beats TDSConv baselines for personalized model

Fast, Flexible and Portable Structured Generation

Unified framework for robot learning built on NVIDIA Isaac Sim

A PyTorch re-implementation of Neural Radiance Fields

[ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

A generative world for general-purpose robotics & embodied AI learning.

Let us control diffusion models!