SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget.
Rui KongYuanchun LiQingtian FengWeijun WangXiaozhou YeYe OuyangLinghe KongYunxin LiuPublished in: ACL (1) (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- speech recognition
- document retrieval
- information retrieval
- query expansion
- retrieval model
- statistical language models
- context sensitive
- language modelling
- vector space model
- test collection
- ad hoc information retrieval
- smoothing methods
- query terms
- language model for information retrieval
- relevance model
- pseudo relevance feedback
- machine learning
- handwriting recognition
- document ranking
- document length
- pseudo feedback
- language models for information retrieval