Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

CUDA/Metal accelerated language model inference

RPyC (Remote Python Call) - A transparent and symmetric RPC library for python

📚 Jupyter notebook tutorials for OpenVINO™

Embree ray tracing kernels repository.

Universal LLM Deployment Engine with ML Compilation

Build system, successor to Buck

MoonRay is DreamWorks’ open-source, award-winning, state-of-the-art production MCRT renderer.

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

Language Modeling with the H3 State Space Model

An open-source efficient deep learning framework/compiler, written in python.

An efficient vector-graphics renderer

A GPU compute-centric 2D renderer.

A modern cross-platform low-level graphics library and rendering framework

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Real-time GPU path tracing with an OpenUSD Hydra render delegate

This is the development repository for the OpenFHE library. The current version is 1.4.2 (released on October 20, 2025).

3D fluid simulation experiments in Rust, using WebGPU-rs (WIP)

A STARK prover and verifier for arbitrary computations

The Flutter engine

A General-purpose Task-parallel Programming System using Modern C++

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Single C file, Realtime CPU/GPU Profiler with Remote Web Viewer

Vulkan and rust experiments, including a spectral path tracer using Vulkan ray tracing extensions

Instant neural graphics primitives: lightning fast NeRF and more

magic-trace collects and displays high-resolution traces of what a process is doing

3D engine with modern graphics

Open Machine Learning Compiler Framework