GoodSpeed: Optimizing Fair Goodput with Adaptive Speculative Decoding in Distributed Edge Inference

Documenti analoghi

• Federated Koopman-Reservoir Learning for Large-Scale Multivariate Time-Series Anomaly Detection
  di: Le, Long Tan, et al.
  Pubblicazione: (2025)
• Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization
  di: Le, Long Tan, et al.
  Pubblicazione: (2023)
• GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources
  di: Du, Boxiao, et al.
  Pubblicazione: (2026)
• Federated PCA on Grassmann Manifold for IoT Anomaly Detection
  di: Nguyen, Tung-Anh, et al.
  Pubblicazione: (2024)
• Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism
  di: Wei, Jinhui, et al.
  Pubblicazione: (2025)