Home » Academics » Christina Giannoula
-
Multi-Tier Memory and Accelerator Optimization for Deep Learning Recommendation Models
-
Heterogeneous Accelerator Design for Disaggregated RAG-based Large Language Models
-
Energy-Efficient Inference Serving for Mixture of Experts (MoE) Large Language Models
-
Multi-Tier Memory and Accelerator Optimization for Deep Learning Recommendation Models
-
Heterogeneous Accelerator Design for Disaggregated RAG-based Large Language Models
-
Energy-Efficient Inference Serving for Mixture of Experts (MoE) Large Language Models
