@article{snapmlaefficientlongcontextmladecodingvi,
  title = {SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining},
  author = {Yifan Zhang and Zunhai Su and Shuhao Hu and Rui Yang and Wei Wu and Yulei Qian and Yuchen Xie and Xunliang Cai},
  year = {2026},
  eprint = {2602.10718},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.10718},
}