Paper-Conference

Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference

Interpretable Analysis of Production GPU Clusters Monitoring Data via Association Rule Mining

Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service

Toward Sustainable HPC: Carbon Footprint Estimation and Environmental Implications of HPC Systems

Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale

Kairos: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resources

MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant GPU Clusters

AI-Enabling Workloads on Large-Scale GPU-Accelerated System: Characterization, Opportunities, and Implications

Great Power, Great Respobsibility: Recommendations for Reducing Energy for Training Language Models

RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances