@article{250511329,
  title = {TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference},
  author = {Raja Gond and Nipun Kwatra and Ramachandran Ramjee},
  year = {2025},
  eprint = {2505.11329},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.11329v1},
}