Jiangfei Duan
- SpotServe: Serving Generative Large Language Models on Preemptible Instances
2023/11/27 by Xupeng Miao, Chunan Shi, Miao, Xupeng +11 · 14 citations
Computer Science · Materials Science · #Topic Modeling #Natural Language Processing Techniques #Machine Learning in Materials Science
- MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
2024/04/02 by Jiangfei Duan, Runyu Lu, Duan, Jiangfei +13 · 10 citations
Engineering · #Power Line Communications and Noise
- Parcae: Proactive, Liveput-Optimized DNN Training on Preemptible Instances
2024/03/21 by Jiangfei Duan, Ziang Song, Duan, Jiangfei +13 · 5 citations
Computer Science · Engineering · #Distributed #FOS: Computer and information sciences #Parallel #Robotics and Automated Systems #Speech Recognition and Synthesis #Topic Modeling #and Cluster Computing (cs.DC)
- MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
2025/05/09 by Haojie Duanmu, Xiuhong Li, Duanmu, Haojie +11 · 9 citations
Computer Science · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Mobile Crowdsensing and Crowdsourcing #Stochastic Gradient Optimization Techniques
- Proteus: Simulating the Performance of Distributed DNN Training
2023/06/04 by Jiangfei Duan, Xiuhong Li, Duan, Jiangfei +11 · 2 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Distributed #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Parallel #Parallel Computing and Optimization Techniques #and Cluster Computing (cs.DC)