Capture and analyze the high-level performance characteristics of graphics applications on Windows.

An open ecosystem of parametric human models and perception stacks, starting with GNM Head.

JAX-based neural network library

[ICLR 2024] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Notebooks, code and documents for the ISPRS Congress tutorial on Earth embeddings

[ECCV 2026] Real-Time Interactive Multi-Target Video Segmentation

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

A simple bitpacking serializer for C++

An integration of the NVIDIA Omniverse RTX (OVRTX) renderer in Maya

Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools

[ECCV'26] Our method creates 3D Gaussian scenes completely autoregressively, allowing for generation, completion, and outpainting with the same model.

Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024, TPAMI 2026

Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024, TPAMI 2026

Extracts Metahuman facial expressions from a Metahuman head.dna file and outputs OBJ's to an output directory.

UE 5.8+ examples and reusable utilities for saving and reloading actors, instanced actors and Mass entities.

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

Framework for writing deep learning training loops. Lightweight, and retaining full freedom to design as you see fits. It handles checkpointing, logging, distributed, compatibility with Dora, and m…

Proof of concept for running moshi/hibiki using webrtc

Rust crate for some audio utilities

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

The Smallest English TTS Model with only 1M parameters

A TTS that fits in your CPU (and pocket)

Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

The open source codebase powering HuggingChat

A Python port of Pi’s minimalist coding agent.

An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.

Hugging Face MCP Server