LLM training in simple, raw C/CUDA

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Squeeze-and-Excitation Networks

Tile primitives for speedy kernels

CUDA Library Samples

NCCL Tests

Automatically exported from code.google.com/p/cuda-convnet2

CUDA Learning guide

CUDA Matrix Factorization Library with Alternating Least Square (ALS)

Instructions, Docker images, and examples for Nsight Compute and Nsight Systems

A repository that compliments gpgpu-sim, providing automated regression scripts, simulation launching utilities and the code + arguments for simulations that complete in a reasonable amount of time…