Search Results for author: Ephrem Wu

Found 3 papers, 1 papers with code

Learning Accurate Integer Transformer Machine-Translation Models

no code implementations3 Jan 2020 Ephrem Wu

We describe a method for training accurate Transformer machine-translation models to run inference using 8-bit integer (INT8) hardware matrix multipliers, as opposed to the more costly single-precision floating-point (FP32) hardware.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.