OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization.
Cong GuoJiaming TangWeiming HuJingwen LengChen ZhangFan YangYunxin LiuMinyi GuoYuhao ZhuPublished in: ISCA (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- retrieval model
- information retrieval
- language modelling
- query expansion
- speech recognition
- ad hoc information retrieval
- smoothing methods
- test collection
- statistical language models
- translation model
- context sensitive
- pseudo relevance feedback
- vector space model
- language models for information retrieval
- okapi bm
- novelty detection
- retrieval effectiveness
- query terms
- co occurrence
- spoken term detection