HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing

Documenti analoghi

• H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inference
  di: Fu, Zizhuo, et al.
  Pubblicazione: (2025)
• MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
  di: Chitty-Venkata, Krishna Teja, et al.
  Pubblicazione: (2025)
• MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache
  di: Xue, Leyang, et al.
  Pubblicazione: (2024)
• ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference
  di: Shen, Zixu, et al.
  Pubblicazione: (2025)
• AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference
  di: Zhong, Shuzhang, et al.
  Pubblicazione: (2024)