cuda-programming

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

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

📚Modern CUDA Learn Notes: 200+ Tensor/CUDA Cores Kernels🎉, HGEMM, FA2 via MMA and CuTe, 98~100% TFLOPS of cuBLAS/FA2.

Sample codes for my CUDA programming book

CUDA Core Compute Libraries

TinyChatEngine: On-Device LLM Inference Library

Thin, unified, C++-flavored wrappers for the CUDA APIs

Safe rust wrapper around CUDA toolkit

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

A self-learning tutorail for CUDA High Performance Programing.

A simple GPU hash table implemented in CUDA using lock free techniques

This is an archive of materials produced for an introductory class on CUDA programming at Stanford University in 2010

Zero to Hero GPU and CUDA for Maths & ML tutorials with examples.

μ-Cuda, COVER THE LAST MILE OF CUDA. With features: intellisense-friendly, structured launch, automatic cuda graph generation and updating.

CudaPAD is a PTX/SASS viewer for NVIDIA Cuda kernels and provides an on-the-fly view of the assembly.

An implementation of HIP that works on CPUs, across OSes.

Accelerated General (FP32) Matrix Multiplication from scratch in CUDA

CUDA kernel author's tools

Speed up image preprocess with cuda when handle image or tensorrt inference