PipeBoost: Resilient Pipelined Architecture for Fast Serverless LLM Scaling

Documenti analoghi

• FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters
  di: Lin, Yanying, et al.
  Pubblicazione: (2025)
• TD-Pipe: Temporally-Disaggregated Pipeline Parallelism Architecture for High-Throughput LLM Inference
  di: Zhang, Hongbin, et al.
  Pubblicazione: (2025)
• λScale: Enabling Fast Scaling for Serverless Large Language Model Inference
  di: Yu, Minchen, et al.
  Pubblicazione: (2025)
• JanusPipe: Efficient Pipeline Parallel Training for Machine Learning Interatomic Potentials
  di: Wang, Hongyu, et al.
  Pubblicazione: (2026)
• PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption
  di: Tan, Yifan, et al.
  Pubblicazione: (2024)