7 papers
Architectural Implications of Agentic AI Workflows
Jirong Yang, Peizhe Liu, Chaojie Zhang +1
Agentic AI is emerging in datacenters, but its architectural implications remain unexplored. We organize agentic workflows in a taxonomy and present its first architectural charact…
AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies
Qiushi Lin, Chaojie Zhang, Ãñigo Goiri +3
The efficiency of a datacenter rests on its control plane policies. Designing these policies is increasingly hard: the hardware-software stack grows fast, the design space is vast…
Provisioning to Runtime Optimization of a 100 MW-Scale AI Cluster
Ehsan K. Ardestani, Leonardo Piga, Jovan Stojkovic +19
The electric power supply for AI data centers is now the most significant bottleneck in the race toward Artificial General Intelligence, surpassing even the constraint of AI accele…
Nexus: Transparent I/O Offloading for High-Density Serverless Computing
JooYoung Park, Kevin Nguetchouang, Jovan Stojkovic +4
Serverless computing relies on extreme multi-tenancy to remain economically viable, driving providers to rely on virtual machines (VMs) that ensure strong isolation and seamless ec…
Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments
Nikoleta Iliakopoulou, Jovan Stojkovic, Chloe Alverti +3
The widespread adoption of LLMs has driven an exponential rise in their deployment, imposing substantial demands on inference clusters. These clusters must handle numerous concurre…
Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework
Jovan Stojkovic, Chaojie Zhang, Ãñigo Goiri +1
The rapid rise of large language models (LLMs) has been driving an enormous demand for AI inference infrastructure, mainly powered by high-end GPUs. While these accelerators offer…