LLM training in simple, raw C/CUDA

A massively parallel, optimal functional runtime in Rust

GPU database engine

NVIDIA-accelerated zero latency video compression library for interactive remoting applications

Fast Fourier Transform implementation, computable on CUDA platform. Seminar project for MI-PRC course at FIT CTU.

2,3d type1,2 nonuniform FFT on GPU

Adjoint NFFT for GPU (CUDA)

CUDA implementation of hidden Markov model training and classification

High performance computing with GPU