PAME: Precision-Aware Multi-Exit DNN Serving for Reducing Latencies of Batched Inferences
PROCEEDINGS OF THE 36TH ACM INTERNATIONAL CONFERENCE ON SUPERCOMPUTING, ICS 2022(2022)
关键词
Deep neural networks,batch inference,multiple exits
AI 理解论文
溯源树
样例

生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要