EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models.
Rongjie YiLiwei GuoShiyun WeiAo ZhouShangguang WangMengwei XuPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- language modelling
- query expansion
- speech recognition
- retrieval model
- information retrieval
- document retrieval
- statistical language models
- document ranking
- language models for information retrieval
- test collection
- smoothing methods
- query terms
- context sensitive
- mixture model
- pseudo relevance feedback
- bayesian networks
- relevance model
- language model for information retrieval