FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization.
Yi ZhangFei YangShuang PengFangyu WangAimin PanPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- speech recognition
- probabilistic model
- document retrieval
- n gram
- information retrieval
- language modelling
- test collection
- mixture model
- retrieval model
- query expansion
- relevance model
- bayesian networks
- statistical language models
- context sensitive
- pseudo relevance feedback
- translation model
- document ranking
- smoothing methods
- vector space model
- language modeling approaches
- word error rate