LLM training in simple, raw C/CUDA

Instant neural graphics primitives: lightning fast NeRF and more

A massively parallel, optimal functional runtime in Rust

Flash Attention in ~100 lines of CUDA (forward pass only)

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.

EGGROLL in C, integer-first training