Efficient Machine Translation with Model Pruning and Quantization
Maximiliana Behnke, Nikolay Bogoychev, Alham Fikri Aji, Kenneth Heafield, Graeme Nail, Qianqian Zhu, Svetlana Tchistiakova, Jelmer Van der Linde, Pinzhen Chen, Sidharth Kashyap, Roman Grundkiewicz
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We participated in all tracks of the WMT 2021 efficient machine translation task: single-core CPU, multi-core CPU, and GPU hardware with throughput and latency conditions. Our submissions combine several efficiency strategies: knowledge distillation, a simpler simple recurrent unit (SSRU) decoder with one or two layers, lexical shortlists, smaller numerical formats, and pruning. For the CPU track, we used quantized 8-bit models. For the GPU track, we experimented with FP16 and 8-bit integers in tensorcores. Some of our submissions optimize for size via 4-bit log quantization and omitting a lexical shortlist. We have extended pruning to more parts of the network, emphasizing component- and block-level pruning that actually improves speed unlike coefficient-wise pruning.