Ultra-Fast Inference & Open-Weight Models

​An evening with FriendliAI during Ignite week!

In town for Ignite? Come close out the day at our office, just one block from Moscone Center, for a casual evening discussing ultra-fast inference and open-weight models.

Open-weight models like GLM, Kimi, DeepSeek, and MiniMax land in more production workloads every month. The quality gaps have narrowed significantly between open and closed models, at a fraction of the cost. What separates a prototype from production scale is serving: how fast the tokens flow, and how much you pay for them.

What to expect:
• Let's talk about the AI stack. Latency and throughput numbers, serving infrastructure, cost tradeoffs vs. closed models, and how it all holds up under agentic workloads.
• Meet and network with other professional builders, founders, and engineers. Some in town for Ignite, some locals, everyone trading notes on what they're exploring.
• Food and drinks are on us, all evening. Make sure you're registered, but no conference badge required.

Capacity is limited. Doors open at 6pm PT. See you then!