The team behind vLLM, the widely-adopted open-source AI inference engine, has spun out their project into a VC-backed startup called Inferact. The company secured $150 million in seed funding at an $800 million valuation, co-led by Andreessen Horowitz and Lightspeed Venture Partners.

Inferact focuses on making AI model inference faster and more cost-efficient. Their core technology, vLLM, optimizes RAM usage and can boost inference speeds by generating multiple tokens simultaneously rather than one at a time. The project originated at UC Berkeley and is now managed by the PyTorch Foundation.

"We see a future where serving AI becomes effortless," said Inferact co-founder Woosuk Kwon. "Today, deploying a frontier model at scale requires a dedicated infrastructure team. Tomorrow, it should be as simple as spinning up a serverless database." AWS and other major cloud providers are already testing the platform.