SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference

Documenti analoghi

• Collaborative Speculative Inference for Efficient LLM Inference Serving
  di: Gao, Luyao, et al.
  Pubblicazione: (2025)
• Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism
  di: Wei, Jinhui, et al.
  Pubblicazione: (2025)
• UELLM: A Unified and Efficient Approach for LLM Inference Serving
  di: He, Yiyuan, et al.
  Pubblicazione: (2024)
• HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
  di: Dong, Jiangwen, et al.
  Pubblicazione: (2025)
• GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources
  di: Du, Boxiao, et al.
  Pubblicazione: (2026)