LLM training in simple, raw C/CUDA

Instant neural graphics primitives: lightning fast NeRF and more

A massively parallel, optimal functional runtime in Rust

DeepEP: an efficient expert-parallel communication library

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Fast parallel CTC.

FlashInfer: Kernel Library for LLM Serving

CUDA accelerated rasterization of gaussian splatting

cuGraph - RAPIDS Graph Analytics Library

FSA/FST algorithms, differentiable, with PyTorch compatibility.

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

Fast CUDA matrix multiplication from scratch

GPU-accelerated Levenberg-Marquardt curve fitting in CUDA

The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )

Parallel CUDA implementation of NON maximum Suppression

This repository contains the CUDA implementation of the paper "Work-efficient Parallel Non-Maximum Suppression Kernels".

TenTrans High-Performance Inference Toolkit