Searching Optimal Floating-Point Format for Sub-8-Bit Large Language Model Inference.
Youngdeok HwangJanghwan LeeJiwoong ParkJieun LimJungwook ChoiPublished in: ICEIC (2024)
Keyphrases
- statistical machine translation
- floating point
- language model
- translation model
- language modeling
- fixed point
- probabilistic model
- information retrieval
- n gram
- document retrieval
- retrieval model
- speech recognition
- instruction set
- query expansion
- context sensitive
- language modelling
- statistical language models
- ad hoc information retrieval
- bayesian inference
- query terms
- test collection
- mixture model
- bayesian networks
- search engine
- relevance model
- statistical models
- dynamic programming