@article{onepooltwocachesadaptivehbmpartitioningf,
  title = {When KV Meets Embeddings: Dynamic GPU Memory Allocation for Accelerating Generative Recommender Serving},
  author = {Wenjun Yu and Shuguang Han and Amelie Chi Zhou},
  year = {2026},
  eprint = {2605.04450},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.04450},
}