This repository was archived by the owner on Jan 5, 2025. It is now read-only.
This repository was archived by the owner on Jan 5, 2025. It is now read-only.
Cube Pruning #12
Description
A decoder with cube pruning translates faster compared with naive beam search by 3.3x on GPUs and 3.5xon CPUs.
Speeding Up Neural Machine Translation Decoding by Cube Pruning