Lignende værker

• Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding
  af: Wang, Zhibin, et al.
  Udgivet: (2025)
• SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
  af: Chen, Liangkun, et al.
  Udgivet: (2025)
• SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models
  af: Chen, Fahao, et al.
  Udgivet: (2025)
• SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission
  af: Zheng, Ce, et al.
  Udgivet: (2026)
• Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution
  af: Wang, Siqi, et al.
  Udgivet: (2024)