HSCONN: Hardware-Software Co-Optimization of Self-Attention Neural Networks for Large Language Models.
Siqin LiuPrakash Chand KuveAvinash KaranthPublished in: ACM Great Lakes Symposium on VLSI (2024)
Keyphrases
- language model
- hardware software
- neural network
- language modeling
- hardware and software
- n gram
- document retrieval
- probabilistic model
- test collection
- hw sw
- information retrieval
- query expansion
- language modelling
- pattern recognition
- statistical language models
- embedded systems
- relevance model
- retrieval model
- multi layer
- multi core processors
- design methodology
- smoothing methods
- fuzzy logic
- document ranking
- language models for information retrieval
- text classification
- bayesian networks