KubeCon + CloudNativeCon + Open Source Summit + AI_dev China 2024

The electric vehicle (EV) industry is rapidly advancing towards a future where intelligence and connectivity are paramount. As we embrace this new era, the challenges in automotive software development escalate, such as software consistency, testing efficiency, data utilization etc., between simulated environments and real-world vehicle runtime environments. In this session, discover how NIO, an innovator in the global EV sphere, harnesses the power of cloud native technologies such as Containerd, Kubernetes, KubeEdge, and AI cloud-edge collaboration. Learn about NIO's journey to augment the development efficiency and quality of EV software, propelling us towards the zenith of vehicular intelligence. Delve into the transformative impact and future prospects of cloud native solutions in revolutionizing the EV landscape.

电动汽车（EV）行业正迅速向着智能和连接至关重要的未来发展。随着我们迎接这个新时代，汽车软件开发中的挑战不断升级，例如在模拟环境和真实车辆运行环境之间的软件一致性、测试效率、数据利用等等。 在这场演讲中，探索全球EV领域的创新者NIO如何利用云原生技术，如Containerd、Kubernetes、KubeEdge和AI云边协作。了解NIO如何提高EV软件开发效率和质量，推动我们走向车辆智能的巅峰。深入探讨云原生解决方案在革新EV领域中的转变影响和未来前景。

Hong Kong and China have an active open source software community, home to 11 million software developers who are at the forefront of AI innovation. Hong Kong and China are ranked in the top 10 largest communities globally for generative AI projects on GitHub, their developers are making a significant impact on the world of open source software. Join us to explore and celebrate China and Hong Kong's contributions to the open source ecosystem and discover how this community is shaping the future of AI and technology.

香港和中国拥有活跃的开源软件社区，拥有1100万软件开发人员，处于人工智能创新的前沿。香港和中国在GitHub上生成式AI项目的社区规模位列全球前十名，他们的开发人员对开源软件领域产生了重大影响。加入我们，一起探索和庆祝中国和香港对开源生态系统的贡献，并了解这个社区如何塑造AI和技术的未来。

Kubernetes is the de facto platform for running workloads at scale. This talk will present KWOK (https://kwok.sigs.k8s.io/), an open-source toolkit that enables the creation and testing of large-scale Kubernetes clusters with minimal resources, even on a laptop.
Shiming Zhang, the creator and maintainer of KWOK, and Yuan Chen, an engineer at NVIDIA GPU Cloud, will outline KWOK's capabilities to generate and manage a large number of virtual nodes that simulate Kubelet APIs and mimic real nodes, allowing for workload deployment and testing. They will discuss practical use cases of KWOK.

The talk will then introduce KWOK's recent enhancements for reliability and fault-tolerance testing, showcasing its ability to simulate failures by injecting targeted faults into nodes and pods. Through examples and demos, the talk will demonstrate how KWOK can be used for reliability testing and evaluating fault-tolerance mechanisms, ultimately improving workload resilience in Kubernetes.



Kubernetes是运行大规模工作负载的事实标准平台。本次演讲将介绍KWOK（https://kwok.sigs.k8s.io/），这是一个开源工具包，可以利用极少的资源（甚至在笔记本电脑上）创建和测试大规模Kubernetes集群。

KWOK的创始人和维护者张世明，以及NVIDIA GPU Cloud的工程师陈源，将详细阐述KWOK的功能，包括生成和管理大量模拟Kubelet API和真实节点的虚拟节点，从而支持工作负载的部署和测试。他们将讨论KWOK的实际使用案例。

演讲还将介绍KWOK最近针对可靠性和容错性测试的增强功能，展示其通过向节点和Pod注入有针对性的故障来模拟故障的能力。通过示例和演示，演讲将展示如何利用KWOK进行可靠性测试和评估容错机制，从而最终提升Kubernetes中工作负载的弹性能力。

LLMs are powerful artificial intelligence models capable of comprehending and generating natural language. However, the conventional methods for running LLMs pose significant challenges, including complex package installations, GPU devices compatibility concerns, inflexible scaling, limited resource monitoring and statistics, and security vulnerabilities on native platforms. WasmEdge introduces a solution enabling the development of swift, agile, resource-efficient, and secure LLMs applications. Kuasar enables running applications on Kubernetes with faster container startup and reduced management overheads. This session will demonstrate running Llama3-8B on a Kubernetes cluster using WasmEdge and Kuasar as container runtimes. Attendees will explore how Kubernetes enhances efficiency, scalability, and stability in LLMs deployment and operations.

LLM是强大的人工智能模型，能够理解和生成自然语言。然而，传统的运行LLM的方法存在重大挑战，包括复杂的软件包安装、GPU设备兼容性问题、不灵活的扩展性、有限的资源监控和统计，以及在本地平台上的安全漏洞。 WasmEdge提出了一种解决方案，可以开发快速、灵活、资源高效和安全的LLM应用程序。Kuasar使应用程序能够在Kubernetes上运行，具有更快的容器启动速度和减少的管理开销。本场演讲将演示如何使用WasmEdge和Kuasar作为容器运行时，在Kubernetes集群上运行Llama3-8B。与会者将探索Kubernetes如何提高LLM部署和运营的效率、可扩展性和稳定性。