@article{leveragingspeculativesamplingandkvcache, title = {Leveraging Speculative Sampling and KV-Cache Optimizations Together for Generative AI using OpenVINO}, author = {Haim Barad and Ekaterina Aidova and Yury Gorbachev}, year = {2023}, eprint = {2311.04951}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.04951v2}, }