Similar Items: MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters
- Sustainable Graph Analytics Workload Scheduling with Evolutionary Reinforcement Learning in Edge-Cloud Systems
- Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs
- OpenG2G: A Simulation Platform for AI Datacenter-Grid Runtime Coordination
- LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling
- LLM-Enhanced Deep Reinforcement Learning for Task Offloading in Collaborative Edge Computing
- Position: LLM Inference Should Be Evaluated as Energy-to-Token Production