BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Living Open Source Foundation - ECPv6.15.13//NONSGML v1.0//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-ORIGINAL-URL:https://livingopensource.org X-WR-CALDESC:Events for Living Open Source Foundation REFRESH-INTERVAL;VALUE=DURATION:PT1H X-Robots-Tag:noindex X-PUBLISHED-TTL:PT1H BEGIN:VTIMEZONE TZID:Africa/Lusaka BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0200 TZNAME:CAT DTSTART:20250101T000000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTART;TZID=Africa/Lusaka:20260317T080000 DTEND;TZID=Africa/Lusaka:20260317T170000 DTSTAMP:20260514T044623 CREATED:20260225T011944Z LAST-MODIFIED:20260313T143204Z UID:5779-1773734400-1773766800@livingopensource.org SUMMARY:Hosting on-premises GenAI DESCRIPTION:« All Events | March 17 @ 8:00 am  – 5:00 pm\n \nCloud AI is powerful. But it demands a stable internet\,  subscription fees\, and trust that your data stays private. For many organizations in Zambia and across the region\, those are not small assumptions.\nThis training is the answer: A full-day hands-on session on March 17th\, where expert Linux and AI trainer Sander van Vugt shows you how to host a fully functional\, ChatGPT-like AI solution inside your own infrastructure. On your own hardware. Offline if needed. With your own documents built in. \nIS THIS FOR YOU?\n\n\n \n You work in IT and want to understand what hosting AI on your own infrastructure actually requires\n \n\n \n Your organization or institution has limited\, expensive\, or unreliable internet access\n \n\n \n You handle sensitive data that cannot or should not leave your premises\n \n\n \n You want to run AI on existing hardware\, without investing in expensive GPUs\n \n\n \n You are a Linux administrator looking to add AI hosting to your skillset\n \n\n \n You want to bring AI capabilities to communities or institutions that have no access to cloud services\n \n\nBY THE END OF THIS DAY\, YOU WILL BE ABLE TO:\n\n\n \n Explain the key components of a self-hosted GenAI setup\, including LLMs and inference engines\, so you can make informed decisions for your organization\n \n\n \n Run a working AI solution on low-end Linux hardware\, without a GPU and without an internet connection\, using llama.cpp\n \n\n \n Optimize a Linux system specifically for AI inference workloads\n \n\n \n Deploy an enterprise-grade AI solution using vLLM on Linux\n \n\n \n Connect your own internal documents to an AI model using RAG\, so the AI answers questions based on your organization’s own data\n \n\n \n Run a scalable\, production-ready AI solution on top of Kubernetes\n \n\nWHY THIS MATTERS BEYOND THE DATA CENTER\nLiving Open Source Foundation sponsors Cheeba Primary School in Mazabuka\, Zambia. The school has no library. Pupils have no reliable way to look things up\, explore topics\, or access knowledge beyond what their teachers can provide in the classroom. \nThe solution covered in this training will be deployed at the school on low-end hardware\, with no internet connection required. Pupils will be able to ask questions and get answers\, in the same way anyone with a smartphone and a data plan can today. \nThat is what on-premises AI makes possible. Attending this 1-day session on March 17th is free. But every donation made during the event by participants will directly contribute to making it happen. \n \nWHAT WE WILL COVER\nMORNING\n\n\n \n Understanding key components for hosting GenAI: LLMs and inference engines\n \n\n \n Hosting GenAI on low-end hardware without a GPU\n \n\n \n Optimizing Linux for AI inference workloads\n \n\n \n Running a hardware-friendly solution based on llama.cpp on Linux\n \n\nAFTERNOON\n\n\n \n Running an enterprise-friendly solution based on vLLM on Linux\n \n\n \n Including your own documents using RAG\n \n\n \n Running a scalable AI solution on top of Kubernetes\n \n\n \n How all of this helps forward schools in rural Zambia\n \n\nPRACTICAL DETAILS\nDate: Tuesday\, March 17thTime: 8 AM to 5 PM CATLocation: Online + Cavendish University\, LusakaPrice: Free \n \n REGISTRATION \nPREREQUISITES\n Participants should be comfortable working with Linux and able to configure it for common tasks. No AI-specific hardware is required\, though having a Linux system to follow along with the demos is strongly recommended. A standard installation of any Red Hat-based distribution or Ubuntu will work fine. \nABOUT YOUR INSTRUCTOR\nSander van Vugt\nSander is a seasoned Linux trainer specializing in High Availability and Linux performance solutions. With 62 published books\, including bestsellers like the Red Hat RHCE/RHCSA Cert Guide\, and over 20 video courses\, he brings extensive expertise to his training. His approach combines academic knowledge with real-world consulting experience\, ensuring practical and cutting-edge Linux insights. \n \nFREQUENTLY ASKED QUESTIONS\nCan I become a member of Living Open Source Foundation?\n Yes please! We would love to welcome you to our community! Contact us at +260963542263 for details on the benefits and membership tiers. \nWhat hardware do I need to bring?\n A laptop or system running a Red Hat-based distribution or Ubuntu is strongly recommended to follow along with the demos. \nDo I need a GPU?\n No. The training specifically covers running AI on low-end hardware without a GPU. Don’t know what that is? Just bring your laptop\, we’ll probably can get it to work. \nCan my organization sponsor or donate hardware for the school deployment?\n That would be great. Please contact us at +260963542263 for the logistics. \nStart hosting your own genai\nWhether you are running a school with no library\, a clinic with sensitive patient records\, a business with unreliable connectivity\, or a government office that cannot send data abroad\, this training gives you the skills to make it work. \n \n Enroll Now URL:https://livingopensource.org/events/hosting-on-premises-genai/ LOCATION:On-Site ATTACH;FMTTYPE=image/jpeg:https://livingopensource.org/wp-content/uploads/2026/02/Hosting-On-PREMISES-GEN-AI-1-1.jpg ORGANIZER;CN="Living Open Source Foundation":MAILTO:info@livingopensource.org END:VEVENT END:VCALENDAR