MSAO: Adaptive Modality Sparsity-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference

Documenti analoghi

• MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
  di: Yang, Zheming, et al.
  Pubblicazione: (2025)
• EC2MoE: Adaptive End-Cloud Pipeline Collaboration Enabling Scalable Mixture-of-Experts Inference
  di: Yang, Zheming, et al.
  Pubblicazione: (2025)
• PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services
  di: Yang, Zheming, et al.
  Pubblicazione: (2024)
• A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference
  di: Zhang, Yida, et al.
  Pubblicazione: (2026)
• HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
  di: Dong, Jiangwen, et al.
  Pubblicazione: (2025)