AI Inference Day with NVIDIA

🌟 Join Us for AI Inference Meetup with NVIDIA 🌟

Step into the future of AI at the AI Inference Meetup with NVIDIA, a developer event in Bengaluru spotlighting the powerful intersection of artificial intelligence and cloud-native technologies. This full-day gathering brings together visionaries, innovators, and practitioners from leading organizations like NVIDIA, Docker, and Nokia, fostering a platform for insightful discussions and hands-on exploration.

What to Expect:

• 🔑 Inspiring Keynotes & Sessions
  Gain exclusive insights from AI and cloud-native pioneers as they share groundbreaking innovations transforming AI inference and deployment.
• 🤝 Networking with Industry Experts
  Engage with industry leaders, developers, and AI practitioners passionate about the future of cloud-native AI. Build connections that spark collaboration and innovation.
• 🔹 Hands-On Learning & Demos
  Explore real-world applications of AI inference, model optimization, and cloud-native deployments with interactive demos and technical deep dives.

Whether you're an AI developer, cloud architect, or tech enthusiast, this event is your gateway to understanding the future of AI inference and how cloud-native technologies are revolutionizing it.

🌐 Join us and be part of the movement shaping the next wave of AI in the cloud!

Register Now: https://forms.gle/VsTp1DWY7GGp4DcP9

Agenda:

• Welcome and Registration (9:00 AM - 4:00 PM)
• 10:00 AM - 10:30 AM - NVIDIA Inference Stack Demystified by Amit Kumar, NVIDIA
• 10:30 AM - 11:45 AM - LLM Inference Optimization and Serving using TensorRT-LLM and NVIDIA Dynamo
  - Advanced techniques for LLM Inference optimization - FP4, FP8, KV-cache reuse, etc - By Utkarsh Uppal, NVIDIA
• 12:00 PM - 12:30 PM - Tea Break
• 12:30 PM - 1:15 PM - Bridging Data & AI: How Cloudera and NVIDIA Drive the Future of Intelligent Enterprises by Manick Mehra, Anukrati Saxena & Navin Agrawal, Cloudera Team
• 1:15 PM - 2:00 PM - GPU-Accelerated AI Inference for Local LLM Development with Docker Model Runner by Ajeet Singh Raina, DevRel, Docker
• 2:00 PM - 2:30 PM - Lunch
• 2:30 PM - 3:00 PM - AI Inference for enhanced performance and accessibility with TensorRT-LLM by Sarvam.AI Team
• 3:00 PM - 3:30 PM - Securing LLM Apps with NVIDIA Nemo Guardrails, Jayita Bhattacharya, Deliotte
• 3:30 PM - 4:00 - Fine-Tuning LLMs Locally with NIM and NVIDIA NIM Microservices: A Live Demo by Manjunath Janardhan, GE Healthcare

Due to the overwhelming number of registrations, we're only allowing entry to those with a confirmation email. Please check your inbox and attend only if you have received a confirmation email.