FlattenQuant: Breaking through the Inference Compute-bound for Large Language Models with Per-tensor Quantization.
Yi ZhangFei YangShuang PengFangyu WangAimin PanPublished in: LREC/COLING (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- speech recognition
- document retrieval
- information retrieval
- language modelling
- retrieval model
- statistical language models
- mixture model
- query expansion
- smoothing methods
- test collection
- context sensitive
- ad hoc information retrieval
- document length
- translation model
- bayesian networks
- query terms
- pseudo relevance feedback
- document ranking
- okapi bm
- statistical language modeling
- term dependencies
- relevance model
- search engine