SpecTr++: Improved transport plans for speculative decoding of large language models
Kwangjun Ahn ⋅ Ahmad Beirami ⋅ Ziteng Sun ⋅ Ananda Theertha Suresh
Abstract
We revisit the question of accelerating decoding of language models based on speculative draft samples, inspired by Y. Leviathan et al. (ICML 2023). Following Z. Sun et al. (NeurIPS 2023) which makes connections between speculative decoding and optimal transport theory, we design improved transport plans for this problem with no sacrifice in computational complexity in terms of the alphabet size.
Chat is not available.
Successful Page Load