Registration is live for Runtime.
Apply to attend our inaugural conference for engineers running AI in production.
October 1st live at The Midway in San Francisco.
Serving a 2.8T model well takes a village.
Grateful to @simon_mo_, @rogerw0108 and everyone at @inferact, who spent five days trading configs and optimizations with us, right up into the early hours of day zero.
And to @Kimi_Moonshot for bringing us together. We're excited to
With Kimi K3 Day-0 on vLLM: Open Frontier Intelligence for Everyone 馃殌
At 2.8 trillion parameters, Moonshot AI's Kimi K3 is one of the most powerful open-weight models ever released. Starting today, you can serve it on vLLM the moment the weights are public.
What K3 brings:
馃
Kimi K3 is live on Modal.
Moonshot has shipped the world's first open 3T-class model, and we're a day zero launch partner.
We trained a custom DFlash speculator for K3's novel architecture so you can run it faster, losslessly. The most capable open model we've worked with by
