@article{dwdpdistributedweightdataparallelismforh,
  title = {DWDP: Distributed Weight Data Parallelism for High-Performance LLM Inference on NVL72},
  author = {Wanqian Li and Jintao Peng and Zongfei Jing and Tianyu Zhang and Ze Long and Xianjie Qiao and Xiaoming Chen and Dongxu Yang and Kefeng Duan and June Yang},
  year = {2026},
  eprint = {2604.01621},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.01621},
}