【论文阅读】Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU
该论文发布在ICCAD’21会议。该会议是EDA领域的顶级会议。基本信息AuthorHardwareProblemPerspectiveAlgorithm/StrategyImprovment/AchievementFuxunYuGPUResourceunder-utilizationContentionSWSchedulingOperator-levelschedulingML-basedsch