How Not Diamond Saved $750K with LLM Routing Engine
For developers, builders, and anyone looking to streamline LLM deployment, cut costs, and boost performance with smarter LLM routing.
📅 : October 22, 2024
⏰ : 11:00 AM – 12:00 PM PDT
📍 : Zoom Webinar
📝 Agenda:
Join us for an insightful session where Tomás, founder and CEO of Not Diamond, will share how his company reduced inference costs by over $750K with their innovative LLM routing engine.
Topics include:
- Introduction to Not Diamond's LLM Routing Engine: How it optimizes model selection to reduce costs and improve efficiency
- The Cost-Saving Impact: A breakdown of how the routing engine achieved a 51% reduction in inference costs
- Live Demo: Watch how a single line of code can implement this routing engine and save costs in real time
- Opportunities to Contribute: Learn about current development priorities and how you can get involved with Not Diamond's open-source initiatives
🎤 Speakers:
Tomás - Founder and CEO of Not Diamond. Tomás co-founded a housing startup, built a digital civic tech platform featured on TIME magazine, and studied math at Brown University and design at RISD. Not Diamond is supported by some of the world's top AI scientists, including Jeff Dean and Ion Stoica.
💫 Why Attend?
In just one hour, learn how Not Diamond's smart routing technology can revolutionize your LLM deployment strategy, cutting costs and boosting performance. See live demonstrations and get insights into how model routing can bring efficiency to your AI infrastructure. Connect directly with Tomás and explore how you can contribute to this evolving space.
🔗 Resources:
Not Diamond Blog: How We Reduced Inference Costs by 51%
Tomás on Twitter: @tomas_hk
LinkedIn: Tomás' Profile