Transformer is the most critical alogrithm innovation in the NLP field in recent years. It brings higher model accuracy while introduces more calculations. The efficient deployment of online Transformer-based services faces enormous challenges. In order to make the costly Transformer online service more efficient, the WeChat AI open-sourced a Transformer inference acceleration tool called TurboTransformers, which has the following characteristics.
- An overview of gradient descent optimization algorithms
- GitHub – AkariAsai/learning_to_retrieve_reasoning_paths: The official implementation of ICLR 2020, « Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering ».