Concept
prompt-lookup decoding
A model-free speculative decoding method that performs n-gram matching directly within the prompt, using segments already present in the prompt as drafts; the draft source is static text.
Timeline (last 90 days)
Oct 26
The draft sources of SuffixDecoding and prompt-lookup decoding are static or semi-static text and are unaware of changes in the policy distribution during training.
Unverified50%
Oct 26
NgramRL's average acceptance length is 7.0 times higher than prompt-lookup decoding's.
Unverified50%