SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission

Documenti analoghi

• Clustering-Based User Selection in Federated Learning: Metadata Exploitation for 3GPP Networks
  di: Zheng, Ce, et al.
  Pubblicazione: (2026)
• Communication-Efficient Distributed On-Device LLM Inference Over Wireless Networks
  di: Zhang, Kai, et al.
  Pubblicazione: (2025)
• FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference
  di: Liu, Xing, et al.
  Pubblicazione: (2025)
• IRS Aided Federated Learning: Multiple Access and Fundamental Tradeoff
  di: Chen, Guangji, et al.
  Pubblicazione: (2024)
• Over-the-Air Federated Learning with Phase Noise: Analysis and Countermeasures
  di: Dahl, Martin, et al.
  Pubblicazione: (2024)