LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management

Documenti analoghi

• TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
  di: Bian, Zhuohang, et al.
  Pubblicazione: (2025)
• Hyper-parameter Optimization for Federated Learning with Step-wise Adaptive Mechanism
  di: Saadati, Yasaman, et al.
  Pubblicazione: (2024)
• ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache
  di: Wang, Shao, et al.
  Pubblicazione: (2026)
• FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training
  di: Dabaja, Ahmad, et al.
  Pubblicazione: (2026)
• Towards Optimal Heterogeneous Client Sampling in Multi-Model Federated Learning
  di: Zhang, Haoran, et al.
  Pubblicazione: (2025)