Instant neural graphics primitives: lightning fast NeRF and more

A massively parallel, optimal functional runtime in Rust

Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

FSA/FST algorithms, differentiable, with PyTorch compatibility.

Efficient GPU kernels for block-sparse matrix multiplication and convolution

Fast CUDA matrix multiplication from scratch

State of the art sorting and segmented sorting, including OneSweep. Implemented in CUDA, D3D12, and Unity style compute shaders. Theoretically portable to all wave/warp/subgroup sizes.

CUDA-accelerated Fully Homomorphic Encryption Library

A fast and highly scalable GPU dynamic memory allocator

A GPU algorithm for sparse matrix-matrix multiplication

CUDA implementation of parallel radix sort using Blelloch scan

Library of common noise functions for CUDA kernels

Efficient CUDA Stream Compaction Library

A simple library-less CUDA implementation of the OneSweep sorting algorithm.