@article{batchllmoptimizinglargebatchedllm,
  title = {BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching},
  author = {Zhen Zheng and Xin Ji and Taosong Fang and Fanghao Zhou and Chuanjie Liu and Gang Peng},
  year = {2024},
  eprint = {2412.03594},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.03594v2},
}