Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs
Yechen Xu · Yifei Wang · Nathanael Ren · Yiran Chen · Danyang Zhuo
摘要
Consumer machines are increasingly running large ML workloads such as large language models (LLMs), text-to-image generation, and interactive image editing. Unlike datacenter GPUs, consumer GPUs serve single-user, rapidly changing workloads, and each model’s working set often nearly fills the GPU...