HGCA: Hybrid GPU-CPU Attention for Long Context LLM Inference

Documenti analoghi

• Architectural and System Implications of CXL-enabled Tiered Memory
  di: Yang, Yujie, et al.
  Pubblicazione: (2025)
• An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference
  di: Yao, Feiyu, et al.
  Pubblicazione: (2026)
• Nomad: Non-Exclusive Memory Tiering via Transactional Page Migration
  di: Xiang, Lingfeng, et al.
  Pubblicazione: (2024)
• HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
  di: Lin, Mao, et al.
  Pubblicazione: (2026)
• Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference
  di: Chung, Euijun, et al.
  Pubblicazione: (2026)