@article{budgetawarecompressionpipelineforsingleg,
  title = {Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects},
  author = {Hongyu Yu and Yifei Shen},
  year = {2026},
  eprint = {2608.30076},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.30076},
}