Minions: Accelerating Large Language Model Inference with Adaptive and Collective Speculative Decoding.
Siqi WangHailong YangXuezhu WangTongxuan LiuPengbo WangXuning LiangKejie MaTianyu FengXin YouYongjun BaoYi LiuZhongzhi LuanDepei QianPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- information retrieval
- language modelling
- test collection
- query expansion
- retrieval model
- speech recognition
- statistical language models
- bayesian inference
- translation model
- ad hoc information retrieval
- query terms
- mixture model
- context sensitive
- web search
- generative model
- word clouds
- vector space model
- pseudo relevance feedback
- document ranking
- smoothing methods
- language model for information retrieval
- document length
- retrieval effectiveness
- statistical models
- text classification
- bayesian networks