Inferact, built by vLLM’s creators, makes AI inference cheaper and faster by expanding open-source support across 500+ model architectures and 200+ accelerator types.

Products & media

vLLM

An open-source inference and serving engine for running large language models efficiently across many architectures and accelerator types.

Cosigns

Matt BornsteinGeneral Partner, a16z infrastructure
“We believe it’s important for a company like Inferact to exist, focusing narrowly on improving the software stack and building what they call the “universal inference layer.””
Source
Zachary XiProduct manager at Inferact
“Beyond the product, what has struck me most is how simultaneously cracked and kind this team is. Everyone here has insane depth of experience, and yet is still so generous with their time and thoughts.”
Source
Kaichao YouCo-founder and Chief Scientist at Inferact
“Our team is full of superheroes!!! After months of hard work, our major project is finally public!”
Source

Team

3 people across company lists

Founders

2 people

List
Roger Wang2026-01
Kaichao You

Current Affiliates

1 person

List
Zachary Xi

Jobs

See all jobs for Inferact here.

All 34 jobs

Funding

All fundraising announcements are based on public sources. Please contact Cosign if you believe there are any discrepancies, or claim the profile to edit.

Data current as of January 2026

Leads

Participating Firms

Angels