The vLLM team officially announced its start-up: raising 150 million US dollars, and You Kaichao, a recipient of the Tsinghua University Special Award, became a co-founder

This round of financing was led by venture capital firms Andreessen Horowitz (a16z) and Lightspeed, with Sequoia Capital, Altimeter Capital, Redpoint Ventures and ZhenFund also participating in the investment.

While Inferact's $150 million angel round financing is smaller than the $1 billion raised by Ilya Sutskever's company SSI, it has already exceeded the $115 million financing of Mistral AI, making it one of the largest seed round financings in history, marking that the industry's emphasis on AI inference infrastructure is rising rapidly.

Inferact's mission is to develop vLLM into the world's leading AI inference engine, and accelerate the development of AI by reducing inference costs and increasing inference speed.

The company believes that the biggest challenge facing the AI industry in the future is not building new models, but how to run existing models with low cost and high reliability.

There is no doubt that the core of Inferact is the open source project vLLM, which was launched in 2023 and aims to help enterprises run AI models efficiently on data center hardware.

vLLM was originally developed by the Sky Computing Lab of the University of California, Berkeley (UC Berkeley), and is now managed by the PyTorch Foundation. It has attracted more than 2,000 contributors from the entire AI industry, and is the most popular open source large model inference acceleration framework around the world.

Nowadays, the inference capability of vLLM powers technology companies such as Meta, Google and Character.AI.

Simon Mo, CEO of Inferact, is a PhD candidate at Berkeley and one of the founding maintainers of vLLM. Mo said that the company was founded in November 2025 and officially announced to the public this week. He compared the origin of Inferact to some early software projects of Berkeley that later developed into larger enterprises, such as Apache Spark and Ray.