CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration

Ähnliche Einträge

• CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters
  von: Huang, Shaoyuan, et al.
  Veröffentlicht: (2026)
• Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud
  von: Ghosh, Himel
  Veröffentlicht: (2024)
• EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting
  von: Yu, Zhongzhi, et al.
  Veröffentlicht: (2024)
• Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration
  von: Wu, Zhiyuan, et al.
  Veröffentlicht: (2023)
• Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design
  von: Xue, Chunyu, et al.
  Veröffentlicht: (2024)