Similar Items: AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework
- Token Arena: A Continuous Benchmark Unifying Energy and Cognition in AI Inference
- Accelerating Precise End-to-End Simulation: Latency-Sensitive Many-core System Modeling
- SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
- Decentralized Stratified Sampling for Low-Latency Approximate Geospatial Data Stream Processing in Edge-Cloud Architectures
- Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel
- Leveraging Teaching on Demand: Approaching HPC to Undergrads