AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Transformer related optimization, including BERT, GPT

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

ijcai19

An open source library for building end-to-end dialog systems and training chatbots.

Question answering over Freebase (single-relation)

some data Competition

Word2Vec - TensorFlow Implementation

Knowledge Base Embedding