@article{kvquanttowards10millioncontextlengthllm,
  title = {KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization},
  author = {Coleman Hooper and Sehoon Kim and Hiva Mohammadzadeh and Michael W. Mahoney and Yakun Sophia Shao and Kurt Keutzer and Amir Gholami},
  year = {2024},
  eprint = {2401.18079},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.18079v5},
}