Generative Pre-Trained Transformer Models From OpenAI

Principles for Faster Transformer Inference

Accelerated Low Bit-Width Neural Network Training

Neural Network Training Trick Improves Model Generalization

Connections Between Tensor Rank and Matrix Rank

Front-End Neural Network Inference

Viewing Neural Networks Remotely

Automatic Differentiation in Forward Mode and Reverse Mode Using PyTorch autograd and functorch

Mathematical Foundations to Neural Network Optimization

Distributed Evaluation for Deep Learning Model on Large Volume of Data