SpecTr: Fast Speculative Decoding via Optimal Transport

Item #:

075280-1314

Details

DOI: https://doi.org/10.52202/075280-1314
Author(s): Ahmad Beirami, Himanshu Jain, Jae Hun Ro, Ziteng Sun, Ananda Theertha Suresh, Felix Yu
Pages: 30222-30242 (21 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/075280-1314
Author(s): Ahmad Beirami, Himanshu Jain, Jae Hun Ro, Ziteng Sun, Ananda Theertha Suresh, Felix Yu
Pages: 30222-30242 (21 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)