Inferact

Inferact is a startup founded by the creators and core maintainers of vLLM, the most popular open-source LLM inference engine. Its mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. As models grow larger and hardware fragments, Inferact works to close the gap so frontier capabilities are not locked behind custom infrastructure. The company plans to push vLLM performance further, deepen support for emerging model architectures, and expand coverage across frontier hardware, with optimizations flowing back to the open-source community that already supports hundreds of model architectures and accelerator types.