چکیده مقاله
Large Language Models LLMs are extremely resource intensive to deploy, demanding high memory and compute Static provisioning often leads to waste or unmet demand We propose a conceptual framework that uses reinforcement learning RL and self adaptive software engineering to optimize resource use in LLM deployments An RL agent monitors system metrics throughput, latency, GPU/CPU utilization and takes actions such as scaling instances, adjusting model precision, or modifying batch sizes The system employs a Monitor Analyze Plan Execute MAPE K loop where dynamic configuration parameters are tuned online to maximize throughput and minimize cost We illustrate the approach with examples: RL driven autoscaling showing ~40–50% higher GPU utilization and adaptive inference optimizations like key value caching up to 4× speedup Real world LLM deployments cloud services and edge settings exhibit highly variable workloads; our framework adapts to these changes Experiments and industry reports show that RL based adaptation can significantly improve resource efficiency and performance
کلیدواژهها
نویسندگان
Parvaneh Asghari
Department of Computer Engineering, CT C , Islamic Azad University, Tehran, Iran
Alireza Rahimipour Anaraki
Department of Computer Engineering, CT C , Islamic Azad University, Tehran, Iran
شیوه ارجاع
Asghari, Parvaneh and Rahimipour Anaraki, Alireza,1404,Resource Optimization in Large Language Model Deployment Using Reinforcement Learning and Adaptive Software Engineering,21st International Conference on Innovation and Research in Engineering Sciences
ارائهشده در
مجموعه مقالات بیست و یکمین کنفرانس بین المللی نوآوری و تحقیق در علوم مهندسی31 تیر 1404