English

Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution

Computation and Language 2024-06-06 v2 Distributed, Parallel, and Cluster Computing Machine Learning

Abstract

The complexity of large language model (LLM) serving workloads has substantially increased due to the integration with external tool invocations, such as ChatGPT plugins. In this paper, we identify a new opportunity for efficient LLM serving for requests that trigger tools: tool partial execution alongside LLM decoding. To this end, we design Conveyor, an efficient LLM serving system optimized for handling requests involving external tools. We introduce a novel interface for tool developers to expose partial execution opportunities to the LLM serving system and a request scheduler that facilitates partial tool execution. Our results demonstrate that tool partial execution can improve request completion latency by up to 38.8%.

Keywords

Cite

@article{arxiv.2406.00059,
  title  = {Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution},
  author = {Yechen Xu and Xinhao Kong and Tingjun Chen and Danyang Zhuo},
  journal= {arXiv preprint arXiv:2406.00059},
  year   = {2024}
}

Comments

11 pages, 8 figures

R2 v1 2026-06-28T16:48:56.525Z