@article{optimizinginferenceintransformerbasedmod, title = {Optimizing Inference in Transformer-Based Models: A Multi-Method Benchmark}, author = {Siu Hang Ho and Prasad Ganesan and Nguyen Duong and Daniel Schlabig}, year = {2025}, eprint = {2509.17894}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.17894}, }