Qi Zhang, Yi Liu, Tao Liu, Depei Qian. CoFB: latency-constrained co-scheduling of flows and batches for deep learning inference service on the CPU-GPU system. The Journal of Supercomputing, 79(13):14172-14199, September 2023. [doi]
@article{ZhangLLQ23,
title = {CoFB: latency-constrained co-scheduling of flows and batches for deep learning inference service on the CPU-GPU system},
author = {Qi Zhang and Yi Liu and Tao Liu and Depei Qian},
year = {2023},
month = {September},
doi = {10.1007/s11227-023-05183-6},
url = {https://doi.org/10.1007/s11227-023-05183-6},
researchr = {https://researchr.org/publication/ZhangLLQ23},
cites = {0},
citedby = {0},
journal = {The Journal of Supercomputing},
volume = {79},
number = {13},
pages = {14172-14199},
}