A C++ header-only Eigen-based Library for Lie group operations

A C++ header-only Eigen-based Library for Lie group operations

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Python bindings for llama.cpp

Python bindings for llama.cpp

GPU Kernels

100 days of building GPU kernels!

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Large-scale LLM inference engine

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

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

Examples from Programming in Parallel with CUDA

Efficient Distributed GPU Programming for Exascale, an SC/ISC Tutorial

hpc 教程，包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels