Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference

Documenti analoghi

• Scaling Large Language Model Training on Frontier with Low-Bandwidth Partitioning
  di: Xu, Lang, et al.
  Pubblicazione: (2025)
• Accelerating Large Language Model Training with Hybrid GPU-based Compression
  di: Xu, Lang, et al.
  Pubblicazione: (2024)
• Demystifying the Communication Characteristics for Distributed Transformer Models
  di: Anthony, Quentin, et al.
  Pubblicazione: (2024)
• The Case for Co-Designing Model Architectures with Hardware
  di: Anthony, Quentin, et al.
  Pubblicazione: (2024)
• Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer
  di: Yao, Jinghan, et al.
  Pubblicazione: (2024)