← Back
@article{behdin2025scaling,
  title={Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search},
  author={Behdin, Kayhan and Song, Qingquan and Vasudevan, Sriram and Sheng, Jian and Ma, Xiaojing and Zhou, Z and Zhu, Chuanrui and Li, Guoyao and Nguyen, Chanh and Ghosh, Sayan and others},
  journal={arXiv preprint arXiv:2510.22101},
  year={2025}
}