vLLM Inference Meetup Wellington
- Date
- 2026-04-23
- Location
- Wellington, Wellington Region, New Zealand
- Host
- vLLM Meetups and Events
About this event
If you’re building with large language models, thinking seriously about inference, or just want to meet other people working on practical AI in Wellington, this meetup is for you. vLLM Inference Meetup Wellington is a chance to spend an evening with local engineers, builders, and curious practitioners who care about making model serving faster, more efficient, and more usable in the real world. About the Event This is an in-person community meetup focused on vLLM and inference: the part of the AI stack where ideas turn into usable systems. The goal is simple: bring together people in Wellington who are interested in serving language models, comparing approaches, sharing lessons from production, and talking openly about what actually works. The format is designed to feel approachable whether you’re deep in the infrastructure side of AI or just starting to explore modern inference tools. Expect a social, technically grounded gathering where you can hear how others are thinking about performance, deployment, developer experience, and the tradeoffs that come with running LLM-powered applications. Because this is a meetup, the emphasis is on conversation as much as content. You won’t just sit through a one-way presentation and leave. You’ll have space to ask questions, swap notes with other attendees, and connect with people who are facing similar engineering and product challenges. What to Expect The evening starts at 5:30 PM on Thursday, April 23 in Wellington, New Zealand. As people arrive, there will be time to settle in, say hello, and get a sense of who’s in the room. Meetups like this work best when attendees bring their own context, so come ready to talk about what you’re building, testing, or trying to understand. You can expect a mix of activities that support both learning and networking, such as: Technical discussion around vLLM inference and the role it plays in modern LLM systems Community conversation about deployment patterns, latency, throughput, scaling, and operational tradeoffs Open networking time to meet local practitioners, founders, engineers, and AI enthusiasts Informal Q&A and idea exchange with people working through similar problems Rather than trying to cover everything about AI, this meetup keeps the focus narrow enough to be useful. That means better conversations about the practical side of inference: how teams think about serving models, where bottlenecks show up, what matters in production, and how tooling choices affect cost, speed, and reliability. Expect an atmosphere that is social and thoughtful. Some attendees may come primarily to learn, others to recruit collaborators, pressure-test ideas, or trade implementation tips. All of those are good reasons to be there. Why Attend If you’ve been following the rapid pace of LLM development, you already know that inference is where many of the hardest practical questions live. It affects user experience, infrastructure cost, system responsiveness, and the feasibility of shipping AI features at all. Spending time with others who care about this layer of the stack can save you time and sharpen your thinking. This meetup gives you a chance to: Learn from peers who are exploring or using vLLM in practical settings Get clearer on inference concepts by hearing how others frame the problem Expand your local network in Wellington’s AI and engineering community Discover common patterns and pain points across teams and projects Have better conversations than you would online, with context, nuance, and follow-up questions in real time Even if you’re early in your understanding of model serving, being in the room can help you connect the dots faster. You’ll leave with a stronger sense of what people mean when they talk about inference performance, what kinds of decisions teams are making today, and where tools like vLLM fit into that picture. For more experienced attendees, the value is different but just as real: meeting other serious builders locally, hearing practical perspectives you may not get from documentation alone, and finding people worth staying in touch with after the event. Practical Details This is an in-person event in Wellington, New Zealand, built around community, discussion, and face-to-face connection. If you get the most value from being able to ask direct questions, read the room, and continue a conversation after a session ends, the in-person format will be a strong fit. Date and time: Thursday, April 23 5:30 PM GMT+12 The meetup is well suited to an after-work crowd, so you can come straight from the office, campus, or your current project and step into a room full of people interested in the same technical space. Since the event centers on networking and shared discussion, it helps to arrive ready to introduce yourself and describe what you’re interested in, even briefly. If vLLM, LLM inference, or the operational side of AI has been on your mind, this is a strong reason to get out from behind your screen and meet the local community in person. Wellington has smart people working across engineering, research, product, and startups. This meetup is a focused place to find them.
Who should attend
If you want sharper conversations about LLM inference and a stronger connection to Wellington’s local AI community, you’ll feel at home here. - You’re an **ML engineer, software engineer, or infrastructure engineer** who cares about model serving, performance, scaling, or deployment tradeoffs. - You’re **building AI products or prototypes** and want to better understand how inference choices affect latency, reliability, cost, and user experience. - You’re **curious about vLLM specifically** and want a practical, community-driven way to learn how people are thinking about it. - You work in a **startup, product team, research group, or independent project** and want to meet others solving related technical problems. - You’re an **AI practitioner or technically minded learner** who benefits from in-person discussion more than passive online reading. - You want to **expand your network in Wellington** with people who can share lessons, challenge your assumptions, and possibly become future collaborators. You do not need to arrive as an expert. What matters most is genuine interest in inference, a willingness to talk with others, and an appetite for practical discussion rather than hype.