@article{rapruntimeadaptivepruningforllm, title = {RAP: Runtime-Adaptive Pruning for LLM Inference}, author = {Huanrong Liu and Chunlin Tian and Xuyang Wei and Jiaheng Dai and Qin Liu and Tianqi Wei and QingBiao Li and Li Li}, year = {2025}, eprint = {2505.17138}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.17138v2}, }