Inferact raises $150M seed round to scale the vLLM inference engine

Inferact, a San Francisco AI infrastructure startup founded by the people who maintain vLLM, has raised $150 million in seed funding. The round, announced on January 22, 2026, valued the company at $800 million post-money.

The investor list includes Andreessen Horowitz and Lightspeed Venture Partners, among others. The pitch is simple: take one of the most widely used open-source tools for running large language models and build a commercial business around it, without closing the source.

What Inferact is actually selling

vLLM tackles inference efficiency with a technique called PagedAttention. The idea borrows from virtual memory, the trick operating systems use to juggle limited RAM across many programs at once.

Instead of reserving large, rigid blocks of memory for each request, the system hands out memory in smaller pages as needed. Less memory sits idle, so the same hardware can serve more requests.

The project’s reach is broad. vLLM supports more than 500 model architectures and over 200 hardware accelerators. More than 2,000 contributors have worked on it.

Amazon, Meta, and Google all use vLLM in their production systems.

Inferact plans to layer paid services on top. Those include serverless offerings, where customers run models without managing servers themselves, and stronger observability tools for monitoring how deployments behave. The company says its focus is tuning inference across three levers: cost, latency, and throughput.

From Berkeley lab to $800 million startup

vLLM began in 2023 at UC Berkeley’s Sky Computing Lab. The lab is directed by Ion Stoica, a co-founder of Databricks.

Stoica is also a founding member of Inferact. The rest of the founding team includes Simon Mo, who serves as CEO, joined by Woosuk Kwon, Kaichao You, and Roger Wang.

In May 2025, vLLM became a PyTorch Foundation project. Inferact was established later in 2025, with a stated goal of commercializing and scaling vLLM while keeping the open-source model intact.

As of October 2026, Inferact continues contributing upstream to vLLM, including early optimization work for NVIDIA’s Vera Rubin hardware. That effort has delivered up to 7.8x throughput improvements on specified models.

What this means for the AI infrastructure market

The open-source commercialization playbook is familiar. Databricks built a business around Apache Spark, another project with Berkeley roots. Inferact is running a similar play, with a founding member who has done it before.

With support for more than 200 accelerators, vLLM is positioned as a layer that works across chip vendors. Large cloud providers already run vLLM themselves, and they have deep pockets and their own managed AI services. Inferact’s stated advantage is expertise: the people who know the codebase best now work under one roof.