類似資料

• TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading
  著者:: Pan, Yudong, 等
  出版事項: (2026)
• MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching
  著者:: Xu, Tairan, 等
  出版事項: (2025)
• MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs
  著者:: Cao, Shiyi, 等
  出版事項: (2024)
• HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
  著者:: Zhong, Shuzhang, 等
  出版事項: (2025)
• Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems
  著者:: Huang, En-Ming, 等
  出版事項: (2025)