⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator

Inference speed / accuracy tradeoff on text classification with transformer models such as BERT, RoBERTa, DeBERTa, SqueezeBERT, MobileBERT, Funnel Transformer, etc.

用于测试mmdetection模型的CPU推理速度