cublas

NumPy & SciPy for GPU

LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

Safe rust wrapper around CUDA toolkit

Python interface to GPU-powered libraries

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

🚀🚀🚀 This repository lists some awesome public CUDA, cuda-python, cuBLAS, cuDNN, CUTLASS, TensorRT, TensorRT-LLM, Triton, TVM, MLIR, PTX and High Performance Computing (HPC) projects.

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Hooked CUDA-related dynamic libraries by using automated code generation tools.

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

Deep Learning library using GPU(CUDA/cuBLAS)

Parallel Computing Library for Linux and macOS & NVIDIA CUDA Wrapper

Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.

A Deep Learning framework with very few dependencies, Written in Rust

Algorithms implemented in CUDA + resources about GPGPU

Cross platform C/C++ utilities.

Harness the power of GPU acceleration for fusing visual odometry and IMU data with an advanced Unscented Kalman Filter (UKF) implementation. Developed in C++ and utilizing CUDA, cuBLAS, and cuSOLVER, this system offers unparalleled real-time performance in state and covariance estimation for robotics and autonomous system applications.

bilibili视频【CUDA 12.x 并行编程入门(C++版)】配套代码

code for benchmarking GPU performance based on cublasSgemm and cublasHgemm

Code for testing the native float16 matrix multiplication performance on Tesla P100 and V100 GPU based on cublasHgemm

Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.