Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference.
Zongyue QinZiniu HuZifan HeNeha PrakriyaJason CongYizhou SunPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- query expansion
- document retrieval
- information retrieval
- probabilistic model
- language modelling
- test collection
- retrieval model
- smoothing methods
- speech recognition
- query terms
- context sensitive
- statistical language models
- ad hoc information retrieval
- pseudo relevance feedback
- document ranking
- language models for information retrieval
- mixture model
- word error rate
- relevance model
- bayesian inference
- document length
- web search
- bayesian networks