Get started
Author

Yizhou Shan

LegoOS: a disseminated, distributed OS for hardware resource disaggregation
2018 · Yizhou Shan, Yutong Huang, et al. · Operating Systems Design and Implementation · 215
ShuffleInfer: Disaggregate LLM Inference for Mixed Downstream Workloads
2025 · Cunchen Hu, Heyang Huang, et al. · ACM Transactions on Architecture and Code Optimization · 189
PDF
Clio: a hardware-software co-designed disaggregated memory system
2022 · Zhiyuan Guo, Yizhou Shan, et al. · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · 130
PDF
MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool
2024 · Hu, Cunchen, Huang, Heyang, et al. · arXiv (Cornell University) · 119
PDF
Distributed shared persistent memory
2017 · Yizhou Shan, Shin-Yeh Tsai, et al. · Symposium on Cloud Computing · 110
InstAttention: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference
2025 · Xiurui Pan, Endian Li, et al. · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · 74
PDF
Storm
2019 · Stanko Novakovic, Yizhou Shan, et al. · ACM International Conference on Systems and Storage · 57
EPIC: Efficient Position-Independent Caching for Serving Large Language Models
2024 · Hu, Junhao, Huang, Wenrui, et al. · arXiv (Cornell University) · 47
PDF
CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference
2024 · Li, Suyi, Lu, Hanfeng, et al. · arXiv (Cornell University) · 29
PDF
SuperNIC: An FPGA-Based, Cloud-Oriented SmartNIC
2024 · Will Lin, Yizhou Shan, et al. · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · 22
PDF
Towards a fully disaggregated and programmable data center
2022 · Yizhou Shan, Will Lin, et al. · ACM SIGOPS Asia-Pacific Workshop on Systems (APSys) · 21
PDF
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning
2025 · Junhao Hu, Wenrui Huang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 20
PDF
HoPP: Hardware-Software Co-Designed Page Prefetching for Disaggregated Memory
2023 · Haifeng Li, Ke Liu, et al. · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · 16
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems
2026 · Chang, Chaokun, Zhou, Yukun, et al. · arXiv (Cornell University) · 12
PDF
BlitzScale: Fast and Live Large Model Autoscaling with O(1) Host Caching
2026 · Dingyan Zhang, Yang Liu, et al. · ACM Transactions on Computer Systems · 12
DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving
2025 · Huang, Heyang, Hu, Cunchen, et al. · arXiv (Cornell University) · 12
PDF
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
2025 · Xiao, Ao, He, Bangzheng, et al. · arXiv (Cornell University) · 11
PDF
DeepServe: Serverless Large Language Model Serving at Scale
2025 · Hu, Junhao, Xu, Jiang, et al. · arXiv (Cornell University) · 10
PDF
SuperNIC: A Hardware-Based, Programmable, and Multi-Tenant SmartNIC
2021 · Shan, Yizhou, Lin, Will, et al. · arXiv (Cornell University) · 10
PDF
Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management
2025 · Zhang, Hang, Shi, Jiuchen, et al. · arXiv (Cornell University) · 8
PDF
The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving
2024 · Zeng, Pai, Ning, Zhenyu, et al. · arXiv (Cornell University) · 6
PDF
Skadi: Building a Distributed Runtime for Data Systems in Disaggregated Data Centers
2023 · Cunchen Hu, Chenxi Wang, et al. · Workshop on Hot Topics in Operating Systems · 6
PDF
Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling
2026 · Yifei Liu, Zuo Gan, et al. · ACM Transactions on Architecture and Code Optimization · 5
Clio: A Hardware-Software Co-Designed Disaggregated Memory System
2021 · Guo, Zhiyuan, Shan, Yizhou, et al. · arXiv (Cornell University) · 5
PDF
Storm: a fast transactional dataplane for remote data structures
2019 · Novakovic, Stanko, Shan, Yizhou, et al. · arXiv (Cornell University) · 4
PDF
Works count: 34
Citation count: 1,158
H-index: 13
I10-index: 19
Year
Topic
Type