Схожие документы

• Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving
  по: Wang, Chao, и др.
  Опубликовано: (2025)
• LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism
  по: Wu, Bingyang, и др.
  Опубликовано: (2024)
• Fast Distributed Inference Serving for Large Language Models
  по: Wu, Bingyang, и др.
  Опубликовано: (2023)
• DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models
  по: Zhang, Zili, и др.
  Опубликовано: (2024)
• TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving
  по: Wu, Bingyang, и др.
  Опубликовано: (2025)