@article{zipservfastandmemoryefficientllminferenc, title = {ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression}, author = {Ruibo Fan and Xiangrui Yu and Xinglin Pan and Zeyu Li and Weile Luo and Qiang Wang and Wei Wang and Xiaowen Chu}, year = {2026}, eprint = {2603.17435}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.17435}, }