Jiangfei Duan

发表论文 13 篇 · 总被引 472 次 · h-index 8

代表论文

• SpotServe: Serving Generative Large Language Models on Preemptible Instances (2023 · International Conference on Architectural Support for Programming Languages and Operating Systems · 被引 155)
• Centauri: Enabling Efficient Scheduling for Communication-Computation Overlap in Large Model Training via Communication Partitioning (2024 · International Conference on Architectural Support for Programming Languages and Operating Systems · 被引 87)
• MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving (2024 · International Conference on Machine Learning · 被引 82)
• Efficient training of large language models on distributed infrastructures: a survey (2024 · Vicinagearth · 被引 58)
• SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention (2024 · Conference on Machine Learning and Systems · 被引 49)
• Parcae: Proactive, Liveput-Optimized DNN Training on Preemptible Instances (2024 · Symposium on Networked Systems Design and Implementation · 被引 47)