3 papers
cs.AR2026
Towards Topology-Aware Very Large-Scale Photonic AI Accelerators
Belal Jahannia, Abdolah Amirany, Hamed Dalir
The rapid growth of deep neural networks (DNNs) has exposed fundamental limitations in electronic accelerators, where data movement dominates energy consumption, commonly referred…
cs.LG2025
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
HamidReza Imani, Jiaxin Peng, Peiman Mohseni +2
The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounc…
cs.DC2024
Mixture of Experts with Mixture of Precisions for Tuning Quality of Service
HamidReza Imani, Abdolah Amirany, Tarek El-Ghazawi
The increasing demand for deploying large Mixture-of-Experts (MoE) models in resource-constrained environments necessitates efficient approaches to address their high memory and co…