Jinyao Liu

As local large language model (LLM) deployment becomes increasingly common, simply exposing inference services like Ollama or vLLM to external users introduces serious security, …

As GPU vendors supporting heterogeneous architectures continue to multiply, their software and hardware ecosystems remain fragmented—effectively forming isolated …

Recently, I’ve taken some time to review recent research papers to explore emerging trends in eBPF and reflect on its evolving landscape. In this article, I focus on the growing …

With the rapid development of machine learning and deep learning, model management and deployment have become important and complex challenges. To simplify this process, we …

AI革命提升了计算需求，加速基础设施建设，但传统网络技术的局限显现。业界需更先进网络解方案以支撑AI性能，UEC联盟于2023年成立，致力于开发高性能、开放的通信架构，以满足AI与HPC的网络需求，引领未来网络技术革新。