DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving
DynBranch is proposed, which makes an unresolved branch addressable before it resolves, and its stable coordinate lets candidate subgraphs run during resolution and completed subgraph results be reused across later requests.
Jun-Yi Shen, Noppanat Wadlom, Zheng-Yuan Su et al.
· 0 citations