@article{blendserveoptimizingofflineinferencefor,
  title = {BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching},
  author = {Yilong Zhao and Shuo Yang and Kan Zhu and Lianmin Zheng and Baris Kasikci and Yang Zhou and Jiarong Xing and Ion Stoica},
  year = {2024},
  eprint = {2411.16102},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.16102v1},
}