1
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
自推测分支技术让LLM agent在等待工具返回时预生成后续推理，大幅减少GPU空闲时间，提升推理效率。
arXiv:2607.03333v1 Announce Type: cross Abstract: LLM agents are becoming a common interface for research, coding, and question answering, yet their T…