C2KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference

Chuheng Du, Junyi Chen, Hanlin Tang, Kan Liu, Tao Lan, Lin Qu, Chaoyue Niu, Shengzhong Liu, Guihai Chen, Fan WuarXiv 2026 · DOI

BibTeX
@misc{du2026c,
  author = {Chuheng Du and Junyi Chen and Hanlin Tang and Kan Liu and Tao Lan and Lin Qu and Chaoyue Niu and Shengzhong Liu and Guihai Chen and Fan Wu},
  title = {{C2KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference}},
  year = {2026},
  eprint = {2607.17715},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.17715},
}

Loading related content...

Figure