Haibing Guan

机构：Shanghai Jiao Tong University · ORCID：0000-0002-4714-7400

发表论文 411 篇 · 总被引 6719 次 · h-index 39

代表论文

• HeShare: Energy-Aware and Efficient Multi-Task GPU Sharing in Heterogeneous GPU-Based Computing Systems (2025 · IEEE Transactions on Computers · 被引 4)
• ASTER: Adaptive Dynamic Layer-Skipping for Efficient Transformer Inference via Markov Decision Process (2025 · 被引 3)
• PLAIN: Leveraging High Internal Bandwidth in PIM for Accelerating Large Language Model Inference via Mixed-Precision Quantization (2025 · 被引 2)
• HEAT: NPU-NDP HE terogeneous A rchitecture for T ransformer-Empowered Graph Neural Networks (2025 · 被引 1)
• Design and Operation of Elastic GPU-Pooling on Campus (2025 · Lecture notes in computer science · 被引 1)
• CELLServe: An SLO-Aware and Cost Efficient LLMs Serving System for Serverless Computing Environments (2026 · ACM Transactions on Architecture and Code Optimization)