Inferact is a new startup founded by the maintainers of vLLM, including Simon Mo, Woosuk Kwon, Kaichao You, and Roger Wang. vLLM is an open-source library for efficient large language model inference and serving. It uses a memory management technique called PagedAttention to optimize throughput and reduce memory usage, supports multiple hardware platforms including NVIDIA and AMD GPUs, and offers various decoding algorithms for operational flexibility.