RecPipe: Co-designing Models and Hardware to Jointly Optimize
Recommendation Quality and Performance

RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance

18 May 2021

Hsien-Hsin S. Lee

David Brooks

Papers citing "RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance"

5 / 5 papers shown

Title
ElasticRec: A Microservice-based Model Serving Architecture Enabling Elastic Resource Scaling for Recommendation Models Yujeong Choi Jiin Kim Minsoo Rhu 32 1 0 11 Jun 2024
Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems Maxim Naumov John Kim Dheevatsa Mudigere Srinivas Sridharan Xiaodong Wang ... Krishnakumar Nair Isabel Gao Bor-Yiing Su Jiyan Yang M. Smelyanskiy GNN 41 83 0 20 Mar 2020
Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems Weijie Zhao Deping Xie Ronglai Jia Yulei Qian Rui Ding Mingming Sun P. Li MoE 57 150 0 12 Mar 2020
RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing Liu Ke Udit Gupta Carole-Jean Wu B. Cho Mark Hempstead ... Dheevatsa Mudigere Maxim Naumov Martin D. Schatz M. Smelyanskiy Xiaodong Wang 41 212 0 30 Dec 2019
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand M. Andreetto Hartwig Adam 3DH 950 20,561 0 17 Apr 2017