@article{llminferenceaccelerationviaefficient,
  title = {LLM Inference Acceleration via Efficient Operation Fusion},
  author = {Mahsa Salmani and Ilya Soloveychik},
  year = {2025},
  eprint = {2502.17728},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.17728v1},
}