FlexLLM: Token-Level Co-Serving of LLM Inference and Finetuning with SLO Guarantees

Documenti analoghi

• AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding
  di: Li, Zikun, et al.
  Pubblicazione: (2025)
• Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems
  di: Miao, Xupeng, et al.
  Pubblicazione: (2023)
• EconoServe: Maximizing Multi-Resource Utilization with SLO Guarantees in LLM Serving
  di: Shen, Haiying, et al.
  Pubblicazione: (2024)
• FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
  di: Chen, Bocheng, et al.
  Pubblicazione: (2024)
• Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking
  di: Mo, Zizhao, et al.
  Pubblicazione: (2026)