S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Documenti analoghi

• Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
  di: Brüel-Gabrielsson, Rickard, et al.
  Pubblicazione: (2024)
• 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)
• SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
  di: Liu, Jianmin, et al.
  Pubblicazione: (2025)
• CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference
  di: Li, Suyi, et al.
  Pubblicazione: (2024)