most citedSpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.MAShow all

1 paper · 1 filter

cs.MA2026

Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective

Noppanat Wadlom, Junyi Shen, Yao Lu

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhib…