In PPoPP ‘25 · Jan 2025

SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs

Yongkang Zhang, Haoxuan Yu, Chenxia Han, Cheng Wang, Baotong Lu, Yunzhe Li, Zhifeng Jiang, Yang Li, Xiaowen Chu, Huaicheng Li

In Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP)

Abstract

This paper presents SGDRC, a software-defined dynamic resource control system for concurrent DNN inference on NVIDIA GPUs.

Conference: PPoPP'25 (30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming)

This paper presents SGDRC, a software-defined dynamic resource control system for concurrent DNN inference on NVIDIA GPUs.

← All publications