1. Serving {DNNs} like clockwork: Performance predictability from the bottom up;gujarati;OSDI 20,2020
2. Nanily: A QoS-Aware Scheduling for DNN Inference Workload in Clouds
3. Salsify: low-latency network video through tighter integration between a video codec and a transport protocol;fouladi;NSDI'18,2018
4. Going deeper with convolutions
5. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding;han,2015