@article{scalableprocessingnearmemoryfor1mtokenll,
  title = {Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits},
  author = {Dowon Kim and MinJae Lee and Janghyeon Kim and HyuckSung Kwon and Hyeonggyu Jeong and Sang-Soo Park and Minyong Yoon and Si-Dong Roh and Yongsuk Kwon and Jinin So and Jungwook Choi},
  year = {2025},
  eprint = {2511.00321},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.00321},
}