@article{llmpqservingllmonheterogeneousclusters,
  title = {LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization},
  author = {Juntao Zhao and Borui Wan and Yanghua Peng and Haibin Lin and Chuan Wu},
  year = {2024},
  eprint = {2403.01136},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.01136v1},
}