As AI inference becomes mainstream, research has begun to focus on improving the energy consumption of inference servers. Inference kernels commonly underutilize a GPU's compute resources and waste power from idling components. To improve utilization and energy efficiency, multiple models can co-locate and share the GPU. However, typical GPU spatial partitioning techniques often experience significant overheads when reconfiguring spatial partitions, which can waste additional energy through repartitioning overheads or non-optimal partition configurations. In this paper, we present ECLIP, a framework to enable low-overhead energy-efficient kernel-wise resource partitioning between co-located inference kernels. ECLIP minimizes repartitioning overheads by pre-allocating pools of CU masked streams and assigns optimal CU assignments to groups of kernels through our resource allocation optimizer. Overall, ECLIP achieves an average of 13% improvement to throughput and 25% improvement to energy efficiency.
@article{arxiv.2506.12598,
title = {ECLIP: Energy-efficient and Practical Co-Location of ML Inference on Spatially Partitioned GPUs},
author = {Ryan Quach and Yidi Wang and Ali Jahanshahi and Daniel Wong and Hyoseung Kim},
journal= {arXiv preprint arXiv:2506.12598},
year = {2025}
}