WEKA and NVIDIA invite you to Blueprint for Scalable AI

Join us for a mid-day break to enjoy lunch, connect with fellow innovators, and explore how the AI infrastructure stack is being reimagined—from accelerating KV cache performance to supporting real-time agents and ultra-large model inference.

Together, WEKA and NVIDIA unlock what’s possible with the next-gen AI stack—combining the Blackwell-powered NVIDIA GB200 platform with WEKA’s high-performance data platform to unlock blazing-fast, cost-efficient, token-optimized AI.

From our experts, you’ll learn:

• How to scale AI workloads efficiently with NVIDIA GB200 and the WEKA Data Platform
• Why KV cache offload to ultra-low-latency storage is critical to accelerating inference at scale
• Best practices for token-optimized architectures that reduce infrastructure cost
• How to eliminate I/O bottlenecks and drive GPU utilization to 90% and beyond

Register today to secure your spot!

Date: Tuesday, June 17, 2025
Time: 11am – 2pm PT
Location: British Bankers Club, 555 Santa Cruz Avenue Menlo Park, CA, 94025