Scholar
Yizhou Shan
Google Scholar ID: qgxGqYAAAAAJ
Huawei Cloud
Disaggregation
Operating System
Distributed System
Computer Architecture
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,456
H-index
14
i10-index
15
Publications
20
Co-authors
0
Publications
9 items
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems
2026
Cited
0
Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation
2026
Cited
0
ReviveMoE: Fast Recovery for Hardware Failures in Large-Scale MoE LLM Inference Deployments
2026
Cited
0
Efficient Serving of LLM Applications with Probabilistic Demand Modeling
2025
Cited
0
DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving
2025
Cited
0
Efficient Long-Decoding Inference with Reasoning-Aware Attention Sparsity
2025
Cited
0
DeepFlow: Serverless Large Language Model Serving at Scale
2025
Cited
0
Fast and Live Model Auto Scaling with O(1) Host Caching
arXiv.org · 2024
Cited
4
Load more
