GTC 2026 Happy Hours: SGLang x RadixArk

​An Exclusive GTC 2026 Happy Hours:
Hosted by SGLang and RadixArk

​Taking a break from the GTC rush? Come hang out with us. 🍝🍷

​We’ve reserved one of the best-rated ⭐ Italian restaurants near the conference — just an easy walking distance from GTC. Expect great food, unlimited drinks, and a relaxed evening with some of the brightest minds in model, inference, and RL infrastructure.

​Researchers and engineers from OpenAI, xAI, DeepMind, Meta, NVIDIA, Ollama, and many cutting-edge startups will be dropping by — come eat, drink, and exchange ideas. 🧠✨

​📅 Date: Tuesday, Mar 17
🕰 Time: 6:30 – 8:30 PM
⏱️Event Agenda:
6:30 PM: Doors Open & Check-in
7:00 PM – 7:15 PM: Banghua Zhu (Co-founder & CTO, RadixArk) | SGLang & RadixArk Presentation
7:15 PM – 7:30 PM: Jason Zhao (Director, Scitix AI) | SIMM: Scalable In-Memory KV Cache for Long-Context
7:30 PM – 8:30 PM: Networking Session

​Note: Capacity is limited; entry will be managed on a first-come, first-served basis.

​
📍 Location: Walking distance from GTC, register to see!
🍷 Dinner, snacks, and unlimited drinks will be served.
Come hungry. Come curious. 🍝🍷

​Last year at GTC, SGLang hosted our very first offline event.
It was the first time we met our community in person — and felt the real energy and support. ❤️

​Over the past year, we’ve been building nonstop ⚡
Faster PR/Issue responses, continuous LLM performance breakthroughs, plus our Diffusion framework, RL framework, and more major releases coming soon.
Let’s push AI infrastructure forward — together. 💥

​​​​​This is a closed-door event and is only open to approved registrants.

​​​​​​🌟About us

​​Co-Host:​

​​SGLang is a high-performance serving framework for large language models and vision-language models, designed to deliver low-latency and high-throughput inference across setups ranging from a single GPU to large distributed clusters. Developed by the LMSYS team (creators of Vicuna and Chatbot Arena) and now part of the PyTorch ecosystem, SGLang has rapidly become the de facto industry standard for LLM inference.
Join SGLang Slack 👉 http://slack.sglang.ai/
Following us on X 👉 https://x.com/lmsysorg?s=20
​If this helps you, please consider giving us a star — it truly motivates the team. ⭐ https://github.com/sgl-project/sglang

RadixArk is an infrastructure-first, deep-tech company with a simple and ambitious mission: "Make frontier-level AI infrastructure open and accessible to everyone."
Following us on X 👉 https://x.com/radixark?s=20

​Partner:

​Z Potentials: A next-generation founder and tech community built around the intersection of AI, frontier technology, and global innovation. With over 1 million followers and 500+ active founder communities, we have hosted 50+ invitation only events and panels with top-tier venture capital firms.
​💼Follow us on LinkedIn (More Founders Interview Coming...)
​💻Visit our WeChat Account (🔍Z Potentials）

​ScitiX AI: A cloud-native infrastructure platform designed to provide a stable digital foundation for the full AI lifecycle. By unifying training, fine-tuning, and inference into a single system, ScitiX enables intelligent scheduling of heterogeneous compute across public, private, and hybrid environments. Built to eliminate infrastructure fragmentation, it empowers teams to scale from experiment to production with absolute cost clarity and reliability.
"Your data in. Your AI service out."
Following us on 👉 X
Following us on 👉 LinkedIn
Join ScitiX on 👉 ​ GitHub