Principles and Techniques of System Performance Optimizations at Different Levels

Matrix Transpose CUDA Kernel Implementation Using CuTe

Mathematical Fundamentals to CUTLASS Computing

General Matrix Multiplication CUDA Performance Optimization

First Principles of Evaluating Deep Learning Inference

One of the Most Widely Used Estimation Methods

Generative Pre-Trained Transformer Models From OpenAI

Principles for Faster Transformer Inference

Create Perfect Error-Correction Hamming Code From Scratch

Mathematical Foundations to Neural Network Optimization

Mathematical Foundations to Neural Network Pruning

Mathematical Foundations to Neural Network Quantization