Search for: All records

Despite the rapid adoption of large language models (LLMs) in mobile applications, deploying them efficiently on resource-constrained devices remains challenging due to limited compute, memory, and energy constraints. In this paper, we first evaluate the energy efficiency of state-of-the-art mobile LLM frameworks across multiple models and uncover a key inefficiency: the default governors make independent decisions which can result in 23.0–40.4% longer latency or 5.0–16.6% higher energy use compared to optimal frequency combinations. We then conduct an in-depth analysis to reveal the root cause–the lack of cross-resource coordination of these governors during prefilling and decoding. Building on these findings, we present CORE, a unified, energy-aware governor that jointly coordinates CPU, GPU, and memory frequencies for mobile LLM inference. Experiments across diverse LLMs show that CORE reduces time-to-first-token by 8.5-17.7% and time-per-token by 27.8-39.6% on average, without increasing energy per token. 

Abstract The California Current System (CCS) is an upwelling eastern boundary ocean current that supports a productive ecosystem through a multitude of physical processes. The fundamental aspects of the ocean circulation are highlighted here and connected to their roles in driving and modulating various components of the California Current Ecosystem (CCE) in the context of pulse and press disturbances. Recent short-term climate events (pulses), such as marine heat waves, that generated highly anomalous responses in the ecology are identified and explained in terms of physical process drivers. The long-term vulnerability of the ecosystem to long-term climate changes (presses) is also discussed. The need for ecologists to collaborate with physical scientists to unravel the press versus pulse impacts on the CCE through sustained physical–ecological observations and high-resolution modeling is emphasized.