Documenti analoghi

• HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing
  di: Huang, Haochen, et al.
  Pubblicazione: (2025)
• An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference
  di: Yao, Feiyu, et al.
  Pubblicazione: (2026)
• Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
  di: Fu, Zizhuo, et al.
  Pubblicazione: (2026)
• PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization
  di: Xu, Tianshi, et al.
  Pubblicazione: (2024)
• HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
  di: Lin, Mao, et al.
  Pubblicazione: (2026)