Speculative decoding

token-level speculative decoding

Superseded baseline#145 of 151 most-superseded

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites token-level speculative decoding as a baseline.

However, existing work either in improving drafting and verification remains token-level, overlooking semantic equivalence between drafts and target outputs, as discussed in Section~sec:intro, which still potentially reject good candidates and leads to low acceptance rate.
Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.