Publications
Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
Chu, Kexin and Lin, Zecheng and Xiang, Dawei and Shen, Zixu and Su, Jianchang and Chu, Cheng and Yang, Yiwei and Zhang, Wenhui and Wu, Wenfei and Zhang, Wei
arXiv preprint arXiv:2508.08438, 2025preprint
eInfer: Unlocking Fine-Grained Tracing for Distributed LLM Inference with eBPF
Chu, Kexin and Su, Jianchang and Zhang, Yifan and Zhao, Chenxingyu and Yang, Yiwei and Zheng, Yusheng and Lin, Shengkai and Zhao, Shizhen and Zhang, Wei
Proceedings of the 3rd Workshop on eBPF and Kernel Extensions, 2025workshop
ChainIO: Bridging Disk and Network Domains with eBPF
Cao, Zheng and He, Xuhang and Hu, Yanpeng and Zheng, Yusheng and Yang, Yiwei and Su, Jianchang and Zhang, Wei and Quinn, Andi
Proceedings of the 3rd Workshop on eBPF and Kernel Extensions, 2025workshop
Runtime Attestation for Secure LLM Serving in Cloud-Native Trusted Execution Environments
Su, Jianchang and Zhang, Wei
Machine Learning for Computer Architecture and Systems, 2025workshop
SPADA: Secure, Performant, and Distributed LLM Inference
Chu, Kexin and Su, Jianchang and Zhang, Wei
Machine Learning for Computer Architecture and Systems, 2025workshop
FastMatch: Enhancing Data Pipeline Efficiency for Accelerated Distributed Training
Su, Jianchang and Jafari, Masoud Rahimi and Zhang, Yifan and Zhang, Wei
2024 IEEE 42nd International Conference on Computer Design (ICCD), 2024conference
PISeL: Pipelining DNN Inference for Serverless Computing
Rahimi Jafari, Masoud* and Su, Jianchang* and Zhang, Yifan and Wang, Oliver and Zhang, Wei
(*Equal contribution)
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024conference
BOAD: Optimizing Distributed Communication with In-Kernel Broadcast and Aggregation
Su, Jianchang and Zhang, Yifan and Huang, Linpu and Zhang, Wei
Proceedings of the ACM SIGCOMM 2024 Workshop on eBPF and Kernel Extensions, 2024workshop
hydns: Acceleration of dns through kernel space resolution
Bardinelli, Joshua and Zhang, Yifan and Su, Jianchang and Huang, Linpu and Parilla, Aidan and Jarvi, Rachel and Kulkarni, Sameer G and Zhang, Wei
Proceedings of the ACM SIGCOMM 2024 Workshop on eBPF and Kernel Extensions, 2024workshop
PINCH: Accelerating Distributed GNN Training through In-Kernel Operation Using eBPF
Su, Jianchang and Zhang, Yifan and Zhang, Wei
Machine Learning for Computer Architecture and Systems, 2024workshop
