@misc{leroux2024analog,
  title={Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models},
  author={Nathan Leroux and Paul-Philipp Manea and Chirag Sudarshan and Jan Finkbeiner and Sebastian Siegel and John Paul Strachan and Emre Neftci},
  year={2024},
  eprint={2409.19315},
  archivePrefix={arXiv},
  primaryClass={cs.NE},
  url={https://arxiv.org/abs/2409.19315}
}