JPPO: Joint Power and Prompt Optimization for Accelerated Large Language Model Services
This work addresses resource efficiency for wireless LLM services, but it is incremental as it builds on existing compression and optimization techniques.
The paper tackles the computational and communication resource demands of large language models in wireless networks by proposing JPPO, a framework that combines prompt compression with power allocation optimization, reducing response time by about 17%.
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.