vLLM Inference Meetup in Sweden 🇸🇪

Hosted by Red Hat AI, AMD, and AI Sweden, this exciting event will take place on 25 March 2026 in Stockholm.

What to Expect:

• Deep technical sessions featuring vLLM maintainers and users sharing their insights at scale 🔍
• Live demonstrations showcasing real workflows in action 💻
• Networking opportunities with food and drinks 🍽️🥤

Who Should Attend:

• vLLM users and contributors 👥
• Machine Learning and infrastructure engineers focused on inference and serving 🔧
• Platform teams running Generative AI in production 🛠️
• Anyone interested in optimizing inference across local, cloud, and Kubernetes environments 💡

Agenda (Subject to More Awesomeness):

• 17:00 – 17:30 — Doors Open, Check-In ✔️
• 17:30 – 17:40 — Welcome and Opening Remarks 🙌
• 17:40 – 18:00 — Introduction to vLLM and Project Update 📊
• 18:00 – 18:30 — Accurate LLM Compression for Fast & Efficient Inference ⚡
• 18:30 – 19:00 — vLLM Inference Optimization on AMD GPUs 🖥️
• 19:00 – 19:15 — Inference Endpoints in the SVEA Project 📈
• 19:15 – 19:45 — Discussion and Q&A ❓
• 19:45 – 21:00 — Networking, Food, and Drinks 🍻

Important Information:

• Registration closes 24 hours before the event. Unregistered attendees cannot be admitted. 🚫
• Please bring a photo ID to verify your registration upon arrival. 📸

See you in Stockholm! If you're building, deploying, or scaling inference, this is the place to be. 🌟

🔗 Register Now!