%0 Conference Paper %1 conf/acl/QianGHSGNS0D24 %A Qian, Haifeng %A Gonugondla, Sujan Kumar %A Ha, Sungsoo %A Shang, Mingyue %A Gouda, Sanjay Krishna %A Nallapati, Ramesh %A Sengupta, Sudipta %A Ma, Xiaofei %A Deoras, Anoop %B ACL (Findings) %D 2024 %E Ku, Lun-Wei %E Martins, Andre %E Srikumar, Vivek %I Association for Computational Linguistics %K dblp %P 8214-8224 %T BASS: Batched Attention-optimized Speculative Sampling. %U http://dblp.uni-trier.de/db/conf/acl/acl2024f.html#QianGHSGNS0D24 %@ 979-8-89176-099-8

@inproceedings{conf/acl/QianGHSGNS0D24, added-at = {2024-08-23T00:00:00.000+0200}, 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}, biburl = {https://www.bibsonomy.org/bibtex/2cb2d9a23fbd6d5dd137874c0fd6426b9/dblp}, booktitle = {ACL (Findings)}, crossref = {conf/acl/2024f}, editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek}, ee = {https://aclanthology.org/2024.findings-acl.489}, interhash = {8e17f53d2d44df38a60d8703c6a8517f}, intrahash = {cb2d9a23fbd6d5dd137874c0fd6426b9}, isbn = {979-8-89176-099-8}, keywords = {dblp}, pages = {8214-8224}, publisher = {Association for Computational Linguistics}, timestamp = {2024-08-26T07:45:49.000+0200}, title = {BASS: Batched Attention-optimized Speculative Sampling.}, url = {http://dblp.uni-trier.de/db/conf/acl/acl2024f.html#QianGHSGNS0D24}, year = 2024 }