HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices.
Xuanlei ZhaoBin JiaHaotian ZhouZiming LiuShenggan ChengYang YouPublished in: CoRR (2024)
Keyphrases
- language model
- resource constrained
- language modeling
- embedded systems
- resource constraints
- n gram
- wireless sensor networks
- probabilistic model
- sensor networks
- document retrieval
- language modelling
- speech recognition
- information retrieval
- rfid tags
- query expansion
- context sensitive
- multipath
- smoothing methods
- test collection
- translation model
- bayesian networks
- query terms
- retrieval model
- pseudo relevance feedback
- relevance model
- document ranking
- vector space model
- statistical language models
- language models for information retrieval
- sensor nodes
- information retrieval systems