Inferact is an AI infrastructure startup founded by the creators and core maintainers of vLLM, an open-source large language model inference engine. Its mission is to advance vLLM as a leading engine for AI inference and accelerate progress by making model serving faster and less expensive. The company addresses the growing complexity of inference as models, architectures, and hardware continue to diversify.

vLLM supports more than 500 model architectures and over 200 accelerator types, serving organizations ranging from frontier research labs and hyperscalers to startups. Built on an ecosystem of more than 2,000 contributors, the project connects model developers, hardware vendors, and teams deploying AI at scale. Inferact aims to improve vLLM’s performance, strengthen support for emerging model architectures, and broaden compatibility with advanced hardware.

The company says its optimizations will flow back to the open-source community, keeping inference infrastructure accessible rather than confined to proprietary systems. Inferact also works on engineering partnerships and production inference capabilities, and is hiring engineers and researchers focused on AI systems