Accelerate AI through Open Source Inference | NVIDIA GTC

The open AI ecosystem is thriving—powered by a new wave of high-performance inference frameworks and community-driven model development. In this session, we hear from ecosystem leaders as they discuss the critical role of open models in progressing AI innovation. We’ll dive deep into the collaborative infrastructure enabling state-of-the-art generative systems—from tokenizer to transformer to GPU kernel. Whether you’re building your own language model, optimizing inference pipelines, or contributing to open AI research, this is your chance to learn about optimization breakthroughs, interoperability standards, and the future of deploying open models at scale. Anu Srivastava | Sr. Technical Marketing Manager | NVIDIA Ofir Bibi | Director of Research | Lightricks Tim Dockhorn | Co-Founder | Black Forest Labs Jeff Boudier | VP of Product | Hugging Face Patrick von Platen | Research Engineer | Mistral AI Key Takeaways: Optimization at the kernel-level is key to driving inference performance. Learn how the future of open source supports enterprise grade applications. Learn how to balance inference throughput with cost for your production applications. Hear from leaders on the future of open source and sovereign AI. Industry: All Industries Topic: Agentic AI / Generative AI - Text Generation Technical Level: Technical - Intermediate Intended Audience: Developer / Engineer NVIDIA Technology: CUDA #nvidiagtc