Bogdan Nicolae
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes adaptive caching for key-value (KV) caching in large language models, improving cache hit rate and reducing time to first token.
Researchers used a large language model to generate checkpoint/restart code for MPI applications, achieving comparable efficiency to human-engineered solutions.
This paper presents two techniques, dynamic checkpointing and progress-aware load redistribution, to maintain forward progress and balanced execution in real-time scientific workflows using the producer-consumer streaming pattern.
Papers
Towards Transparent Checkpointing with AI-driven Code Generation
Hai Duc Nguyen, Tekin Bicer, Kyle Chard, Ian Foster +1 more
Researchers used a large language model to generate checkpoint/restart code for MPI applications, achieving comparable efficiency to human-engineered solutions.