5 papers
ReviveMoE: Fast Recovery for Hardware Failures in Large-Scale MoE LLM Inference Deployments
Haley Li, Xinglu Wang, Cong Feng +12
As LLM deployments scale over more hardware, the probability of a single failure in a system increases significantly, and cloud operators must consider robust countermeasures to ha…
LLM-based Vulnerability Detection at Project Scale: An Empirical Study
Fengjie Li, Jiajun Jiang, Dongchi Chen +1
As software complexity grows, automated vulnerability detection becomes increasingly important. Recent LLM-based detectors combine semantic reasoning with static analysis for proje…
Quark: A High-Performance Secure Container Runtime for Serverless Computing
Chenxingyu Zhao, Yulin Sun, Ying Xiong +1
Secure container runtimes serve as the foundational layer for creating and running containers, which is the bedrock of emerging computing paradigms like microservices and serverles…
Hibernate Container: A Deflated Container Mode for Fast Startup and High-density Deployment in Serverless Computing
Yulin Sun, Deepak Vij, Fenge Li +2
Serverless computing is a popular cloud computing paradigm, which requires low response latency to handle on-demand user requests. There are two prominent techniques employed for r…
TSoR: TCP Socket over RDMA Container Network for Cloud Native Computing
Yulin Sun, Qingming Qu, Chenxingyu Zhao +3
Cloud-native containerized applications constantly seek high-performance and easy-to-operate container network solutions. RDMA network is a potential enabler with higher throughput…