2 papers
cs.DC2026
Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving
Jianru Ding, Ryien Hosseini, Pouya Mahdi Gholami +2
LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives. Existing mult…
cs.AR2024
UpDown: Programmable fine-grained Events for Scalable Performance on Irregular Applications
Andronicus Rajasukumar, Jiya Su, Yuqing +12
Applications with irregular data structures, data-dependent control flows and fine-grained data transfers (e.g., real-world graph computations) perform poorly on cache-based system…