Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding.
Jun ZhangJue WangHuan LiLidan ShouKe ChenGang ChenSharad MehrotraPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- information retrieval
- mixture model
- speech recognition
- language modelling
- retrieval model
- context sensitive
- ad hoc information retrieval
- test collection
- query expansion
- statistical machine translation
- smoothing methods
- statistical language models
- query terms
- pseudo relevance feedback
- translation model
- statistical language modeling
- document ranking
- word error rate