Cover Image for 🧠 GenAI Collective x Novita AI 🌩️ GTC After Hours: Next-Gen AI Inference with NVIDIA, SGLang & vLLM
Cover Image for 🧠 GenAI Collective x Novita AI 🌩️ GTC After Hours: Next-Gen AI Inference with NVIDIA, SGLang & vLLM
Avatar for The GenAI Collective
387 Going

🧠 GenAI Collective x Novita AI 🌩️ GTC After Hours: Next-Gen AI Inference with NVIDIA, SGLang & vLLM

Register to See Address
Sunnyvale, California
Registration
Approval Required
Your registration is subject to approval by the host.
Welcome! To join the event, please register below.
About Event

Novita AI and the GenAI Collective are teaming up to host a high-energy, after-hours event during NVIDIA GTC, dedicated to uncovering the latest breakthroughs in GenAI inference. Connect with industry leaders, top researchers, engineers and founders driving the next generation of AI technologies.

🌟 What You'll Experience:

  • Deep Insights & Practical Techniques: Learn cutting-edge strategies for accelerating GenAI inference from experts shaping the future of AI.

  • Real-world Success Stories: Gain actionable knowledge from prominent projects and companies pushing the boundaries of AI performance and efficiency.

  • Networking Opportunities: Build meaningful connections with over 100 AI researchers, engineers, and founders in a vibrant and relaxed atmosphere.

🍹 Complimentary food and drinks provided!


Agenda:

6:30 - 7:15: Doors Open & Networking

7:15 - 8:30: Expert Panel & Interactive Q&A

🎤 Featured Panelists:

  • Zhiyu (Edward) Cheng, AI/ML Manager @ NVIDIA
    Edward leads algorithm and software development efforts focused on optimizing large-scale inference for generative AI workloads, including Large Language Models (LLMs), Vision-Language Models (VLMs), and diffusion models, on NVIDIA’s latest platforms.

  • Simon Mo, Co-Lead @ vLLM, Compute & Inference Lead @ Character AI
    Simon co-leads the vLLM project and heads the compute and inference team at Character AI, where he specializes in building high-performance inference systems for large-scale generative AI. He has extensive experience optimizing inference engines since 2018, notably leading the development of Ray Serve from 0 to 1 at Anyscale.

  • Chenyang Zhao, Co-Lead @ SGLang (LMSYS Org)
    Chenyang co-leads the SGLang project and is a core contributor at LMSYS Org. His work focuses on facilitating full post-training lifecycle of Large Language Models, including dataset curation, model evaluation, Reinforcement Learning with Human Feedback (RLHF), and efficient inference.

  • Moderator: Junyu Huang, COO @ Novita AI

8:30 – 9:30 PM: Continued Networking & Collaboration


📍 Reserve your spot now—space is limited!


Organizers:

Novita AI is a leading AI cloud platform empowering developers and enterprises to seamlessly serve and scale open source AI models. By fostering a community of innovators, we aim to drive the evolution of open source AI and unlock the full potential of GenAI inference technology.

​​The GenAI Collective is a non-profit, grassroots community of 25,000+ founders, researchers, operators, and investors with chapters in most of the world's global tech hubs. We’re committed to advancing technological progress by increasing the amount of collaboration among people and institutions working on AI, and we facilitate this through world-class events, workshops, and community-led research.

Community Partners:

LMSYS: Large Model Systems (LMSYS Corp.) is a 501(c)(3) non-profit focused on incubating open-source projects and research. Our mission is to make large AI models accessible to everyone by co-developing open models, datasets, systems, and evaluation tools. We conduct cutting-edge machine learning research, develop open-source software, train large language models for broad accessibility, and build distributed systems to optimize their training and inference.

vLLM: vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.

Co-hosts:

Beta University: ​Beta University democratizes Silicon Valley innovation for global talents, via a rigorous incubation program and certificate course. We incubate 200 pre-funding companies every year and help them get funded via top accelerators and angel investors.

FounderCoHo: ​​​​FounderCoHo is a community where founders support each other by sharing knowledge and building connections. Starting a company is a brave endeavor. Many of us have faced numerous challenges and learned valuable lessons along the way. FounderCoho aims to be that supportive community where founders can share their stories and get fueled for their company-building journey.

Plug and Play Tech Center: Plug and Play is the largest open innovation platform that brings together the best startups, the world's largest corporations and seasoned investors. It aims to drive the future forward with corporations, governments, startups, investors, and universities.

Disclaimer: NVIDIA’s involvement in this event is limited solely to the technical insights provided by its invited speaker. This event is not sponsored or endorsed by NVIDIA. Any opinions expressed by NVIDIA representatives are their own and do not necessarily reflect official NVIDIA policy.

All attendees and organizers at GenAI Collective-affiliated events are subject to the GenAI Collective's Code of Conduct.

Location
Please register to see the exact location of this event.
Sunnyvale, California
Avatar for The GenAI Collective
387 Going