Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models (bibtex)

@inproceedings{ZhaoAISTATS25,
  author    = {Zhao, Siyan and Israel, Daniel and Van den Broeck, Guy and Grover, Aditya},
  title     = {Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models}, 
  booktitle = {Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS)},
  month     = {may},
  year      = {2025},
  url       = "https://arxiv.org/pdf/2404.09529.pdf",
  keywords  = {conference,selective}
}