@article{queueinganalysisofgpubasedinference, title = {Queueing Analysis of GPU-Based Inference Servers with Dynamic Batching: A Closed-Form Characterization}, author = {Yoshiaki Inoue}, year = {2019}, eprint = {1912.06322}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1912.06322v3}, }