Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA

Documenti analoghi

• Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
  di: Brüel-Gabrielsson, Rickard, et al.
  Pubblicazione: (2024)
• ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache
  di: Wang, Shao, et al.
  Pubblicazione: (2026)
• S-LoRA: Serving Thousands of Concurrent LoRA Adapters
  di: Sheng, Ying, et al.
  Pubblicazione: (2023)
• InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models
  di: Chen, Hongyu, et al.
  Pubblicazione: (2026)
• Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems
  di: Jaiswal, Shashwat, et al.
  Pubblicazione: (2025)