The explosive growth of interactive Large Language Models (LLMs) has placed unprecedented demands for low latency on cloud GPUs, forcing them into high-power modes and causing escalating energy costs. Real-time inference workloads exhibit significant dynamic volatility, presenting substantial energy-saving opportunities. However, traditional static or rule-based power management strategies struggle to exploit these opportunities without compromising peak performance. To address this challenge, we propose AGFT (An Adaptive GPU Frequency Tuner), a framework that employs online reinforcement learning to autonomously learn an optimal frequency tuning policy. By monitoring real-time features like request load and latency, AGFT utilizes fine-grained frequency control for precise adjustments and intelligent action space pruning for stable, efficient decision-making. This creates a robust, automated energy management solution. We comprehensively evaluated AGFT in an environment simulating realistic, fluctuating inference requests. The experimental results demonstrate that AGFT successfully saves 44.3% of GPU energy consumption while introducing a minimal performance latency overhead of under 10%. This achievement translates into a comprehensive Energy-Delay Product (EDP) optimization of up to 40.3%, clearly showing that our framework can significantly enhance the energy efficiency and economic benefits of existing LLM inference clusters without compromising service quality.<\/p>\n","protected":false},"excerpt":{"rendered":"
The explosive growth of interactive Large Language Models (LLMs) has placed unprecedented demands for low latency on cloud GPUs, forcing them into high-power modes and causing escalating energy costs. Real-time inference workloads exhibit significant dynamic volatility, presenting substantial energy-saving opportunities. However, traditional static or rule-based power management strategies struggle to exploit these opportunities without compromising […]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,3],"tags":[1782,344,2155,20,2154,2090],"class_list":["post-30082","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-paper","tag-computer-science","tag-energy-efficient-computing","tag-llm","tag-nvidia","tag-nvidia-a800","tag-nvidia-rtx-a6000"],"views":877,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/30082","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=30082"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/30082\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=30082"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=30082"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=30082"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}