@article{acceleratingllminferencewithlossless,
  title = {Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies},
  author = {Nadav Timor and Jonathan Mamou and Daniel Korat and Moshe Berchansky and Oren Pereg and Gaurav Jain and Roy Schwartz and Moshe Wasserblat and David Harel},
  year = {2025},
  eprint = {2502.05202},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.05202v1},
}