Skip to content

BASS: Batched Attention-optimized Speculative Sampling.

Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Xiaofei Ma, Anoop Deoras

VenueA*ACL
Year2024
ProceedingsACL (Findings)

Browse the full ACL paper archive.