We have 4 of 26 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Multi-billion-parameter LLMs now run on phones for inference, and training them on the device would personalize them without user data leaving the phone. Prior work has measured individual training steps of such models on phones, but not complete training runs, and not whether adapters trained on the device improve per...
LLM-learned shuttling compilation is feasible, and it is shown how far it currently reaches, and preliminary evidence of cross-architecture generalization is shown.
This paper presents an in-depth analysis of data migration behavior in commercial HSSs, uncovering substantial performance variability when multiple migration tasks execute concurrently, and proposes PASCAL, a system-level bandwidth orchestration framework that improves performance robustness in production-grade HSSs.
The results show that an unmodified frontier LLM can produce working, correct, and competitive shuttling compilers without additional manual algorithmic engineering, thus reducing the development time for new architectures from several months to a few days.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
