Open-source projects tagged “cuda”

An open-source interactive world model from Skywork AI that renders playable game scenes frame by frame with a causal video model on top of an executable game engine.

A GPU-over-IP bridge that lets CPU-only machines use GPUs installed on remote servers over the network.

Open-source, fully local voice studio for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages.

Open-source local AI voice studio for cloning voices, generating speech, dictating into any app, and giving AI agents a voice.

A cross-OS terminal UI and documentation hub for setting up Windows, Linux, macOS, WSL2, Google TV, Stremio and Home Assistant.

A pure C inference engine that runs very large mixture-of-experts models on ordinary hardware by streaming routed experts from disk.

Robotics inference toolkit built on the ApxInf Rust engine, running VLA policies such as PI-0.5 on NVIDIA Jetson and RTX GPUs.

Windows desktop studio for the open YuE2 song model that generates full songs with vocals, an editable ABC score, covers and exact replay on a local NVIDIA GPU.

Open source inference engine that tunes its kernels to your hardware to run each open model as fast as possible.

A learn-by-building ML course: a from-scratch NumPy deep learning framework (CLI) plus 350+ browser-based coding questions.

A Windows portable package that runs the Hunyuan3D 2.0 and 2.1 image-to-3D Gradio web apps without manual environment setup.

An interactive terminal viewer and monitor for NVIDIA GPU devices and the processes running on them, with Python APIs for building custom tools.