@inproceedings{qian-etal-2024-bass, title = "{BASS}: Batched Attention-optimized Speculative Sampling", author = "Qian, Haifeng and Gonugondla, Sujan Kumar and Ha, Sungsoo and Shang, Mingyue and Gouda, Sanjay Krishna and Nallapati, Ramesh and Sengupta, Sudipta and Ma, Xiaofei and Deoras, Anoop", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Findings of the Association for Computational Linguistics: ACL 2024", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.findings-acl.489/", doi = "10.18653/v1/2024.findings-acl.489", pages = "8214--8224" }