

GenAI at scale - a deep dive
GenAI at Scale: Token Economics, Model Choice, & Millisecond Latency
Join hosts AWS, OMERS Ventures, Fireworks and Loka for a deep‑dive into GenAI model choice and token economics from real customers building and scaling on AWS. Hear from AI teams who are helping their customers push the boundaries of throughput, latency and cost efficiency.
The Agenda
9am – 9:45am: Arrival & networking
9:45am – 10am: A welcome from OMERS Ventures (Laura, Partner & Marissa, Investor)
10am – 11am: GenAI Model Choice (Colin from AWS)
11am – Noon: Nova Models (Emily from Loka)
Noon – 1pm: Open Source Trends, High Throughput/Low Latency Use Cases (Shaunak from Fireworks)
1pm – 2pm: Panel Pricing Discussion (Colin/Emily/Shaunak)
*Lunch will be provided*
We are officially part of Toronto Tech Week 2025, a weeklong citywide collection of events to connect and celebrate the builders. June 23 → June 27, 2025 | torontotechweek.com.