Wenyan Chen

Greetings! I am a Postdoctoral Researcher in the Hyperscale Systems and Cloud Architecture Lab at Nanyang Technological University (NTU), Singapore, working with Prof. Dmitrii Ustiugov. Previously, I was a PhD student at the Cloud and Distributed Systems (CDS) Lab at University of Macau (2021.08–2025.08), co-supervised by Prof. Huanle Xu (徐欢乐) and Prof. Kejiang Ye (叶可江).

Research Interests

• GPU virtualization: time-slicing/MPS-style sharing, performance modeling, and interference-aware placement for co-located workloads
• LLM inference systems: Adaptive KV-cache management, prefill–decode optimization for throughput/latency trade-offs
• Multimodal/VLM serving: token explosion mitigation and low-latency inference for streaming video inputs
• Agentic workflows: tool-calling/RAG pipelines, cache-aware multi-step execution, and multi-agent concurrency on shared GPU infrastructure