vLLM team launches Inferact, powers new HUMAIN-M3 Arabic frontier model's inference

woosuk_k · x · 2026-09-04

The core vLLM team has unveiled their new company Inferact, focused on the hardest problems in AI inference: optimizing token quality with model vendors and deployment for sovereign AI partners, claiming large throughput gains even under strict constraints. First public win: HUMAIN-M3, a frontier Arabic model from HUMAIN and MiniMax, runs on vLLM under the hood and is live on HUMAIN Node. The team is hiring and open to compute partnerships.

Original post →

More from Infra

Infra channel →