Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques

Ähnliche Einträge

• Improved Decision Module Selection for Hierarchical Inference in Resource-Constrained Edge Devices
  von: Behera, Adarsh Prasad, et al.
  Veröffentlicht: (2024)
• Exploring the Boundaries of On-Device Inference: When Tiny Falls Short, Go Hierarchical
  von: Behera, Adarsh Prasad, et al.
  Veröffentlicht: (2024)
• Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge
  von: Abstreiter, Maximilian, et al.
  Veröffentlicht: (2025)
• A Survey on Model-heterogeneous Federated Learning: Problems, Methods, and Prospects
  von: Fan, Boyu, et al.
  Veröffentlicht: (2023)
• Inference Offloading for Cost-Sensitive Binary Classification at the Edge
  von: Moothedath, Vishnu Narayanan, et al.
  Veröffentlicht: (2025)