@article{optimizedspeculativesamplingforgpu, title = {Optimized Speculative Sampling for GPU Hardware Accelerators}, author = {Dominik Wagner and Seanie Lee and Ilja Baumann and Philipp Seeberger and Korbinian Riedhammer and Tobias Bocklet}, year = {2024}, eprint = {2406.11016}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.11016v2}, }