{"id":"vllm","name":"vLLM","maker":"vLLM project","url":"https://vllm.ai","repo":"vllm-project/vllm","docs":"https://docs.vllm.ai","package":"pypi:vllm","summary":"A high-throughput inference and serving engine for language models, with an OpenAI-compatible server.","details":"vLLM uses paged attention and continuous batching, and serves models from Hugging Face on NVIDIA, AMD and other accelerators. It is installed as a Python package or Docker image and is hosted by the PyTorch Foundation. It targets servers, not desktops.","open_source":true,"hosted":false,"speaks":["openai-api"],"verified":"2026-11-15","category":"runtimes","category_name":"Local and self-hosted model runtimes","page":"https://modelmoot.com/tools/vllm","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}