DOPD: A Dynamic PD-Disaggregation Architecture for Maximizing Goodput in LLM Inference Serving

Documenti analoghi

• Cloud Native System for LLM Inference Serving
  di: Xu, Minxian, et al.
  Pubblicazione: (2025)
• UELLM: A Unified and Efficient Approach for LLM Inference Serving
  di: He, Yiyuan, et al.
  Pubblicazione: (2024)
• BucketServe: Bucket-Based Dynamic Batching for Smart and Efficient LLM Inference Serving
  di: Zheng, Wanyi, et al.
  Pubblicazione: (2025)
• Auto-scaling Approaches for Microservice Applications: A Survey and Taxonomy
  di: Xu, Minxian, et al.
  Pubblicazione: (2025)
• DRPC: Distributed Reinforcement Learning Approach for Scalable Resource Provisioning in Container-based Clusters
  di: Bai, Haoyu, et al.
  Pubblicazione: (2024)