The Synergy of Speculative Decoding and Batching in Serving Large Language Models.
Qidong SuChristina GiannoulaGennady PekhimenkoPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- speech recognition
- retrieval model
- document retrieval
- query expansion
- information retrieval
- context sensitive
- statistical language models
- language modelling
- pseudo relevance feedback
- vector space model
- smoothing methods
- ad hoc information retrieval
- query terms
- translation model
- document length
- test collection
- machine learning
- text retrieval
- document ranking
- term dependencies
- word error rate