Search papers, labs, and topics across Lattice.
DisNet Lab, The University of Melbourne, University of Melbourne, Melbourne, Australia
3
1
5
Achieve near-instant (<50ms) service downtime when dynamically reconfiguring LLM inference pipelines across heterogeneous GPUs in serverless environments.
Circuit cutting introduces substantial end-to-end overheads in quantum neural network training, with reconstruction dominating per-query time, but surprisingly, test accuracy and robustness can be preserved or even improved.
Current service orchestration solutions fall short of achieving autonomous, resilient, and scalable performance in the Computing Continuum, highlighting the urgent need for standardized evaluation environments.