@article{collaborativelargelanguagemodelinference,
  title = {Collaborative Large Language Model Inference via Resource-Aware Parallel Speculative Decoding},
  author = {Jungyeon Koh and Hyun Jong Yang},
  year = {2025},
  eprint = {2511.01695},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.01695},
}