S-HPLB: Efficient LLM Attention Serving via Sparsity-Aware Head Parallelism Load Balance

Documenti analoghi

• Kairos: Low-latency Multi-Agent Serving with Shared LLMs and Excessive Loads in the Public Cloud
  di: Chen, Jinyuan, et al.
  Pubblicazione: (2025)
• SageSched: Efficient LLM Scheduling Confronting Demand Uncertainty and Hybridity
  di: Gan, Zhenghao, et al.
  Pubblicazione: (2026)
• GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources
  di: Du, Boxiao, et al.
  Pubblicazione: (2026)
• Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
  di: Bu, Tianci, et al.
  Pubblicazione: (2026)
• LLMSched: Uncertainty-Aware Workload Scheduling for Compound LLM Applications
  di: Zhu, Botao, et al.
  Pubblicazione: (2025)