@article{hashattentionsemanticsparsityforfaster, title = {HashAttention: Semantic Sparsity for Faster Inference}, author = {Aditya Desai and Shuo Yang and Alejandro Cuadron and Ana Klimovic and Matei Zaharia and Joseph E. Gonzalez and Ion Stoica}, year = {2024}, eprint = {2412.14468}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.14468v1}, }