JPPO: Joint Power and Prompt Optimization for Accelerated Large Language Model Services

TL;DR

JPPO is a framework that combines prompt compression and wireless power optimization using deep reinforcement learning to enhance large language model services in wireless networks, reducing response time and resource usage.

Contribution

It introduces a novel joint optimization framework that integrates prompt compression with power allocation for wireless LLM services, improving efficiency and service quality.

Findings

Reduces response time by about 17%.

Achieves high service fidelity and low bit error rates.

Effectively balances resource efficiency with service quality.

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, leading to their increasing deployment in wireless networks for a wide variety of user services. However, the growing longer prompt setting highlights the crucial issue of computational resource demands and huge communication load. To address this challenge, we propose Joint Power and Prompt Optimization (JPPO), a framework that combines Small Language Model (SLM)-based prompt compression with wireless power allocation optimization. By deploying SLM at user devices for prompt compression and employing Deep Reinforcement Learning for joint optimization of compression ratio and transmission power, JPPO effectively balances service quality with resource efficiency. Experimental results demonstrate that our framework achieves high service fidelity and low bit error rates while optimizing power usage in wireless LLM services. The system reduces response time by about 17%, with the improvement varying based on the length of the original prompt.