{"id":"vllm","name":"vLLM","tagline":"High-throughput model serving for GPUs.","description":"The production engine for serving open models on your own GPUs.","website":"https://vllm.ai","source":"https://github.com/vllm-project/vllm","license":"Apache-2.0","self_hostable":true,"vendor":{"id":"vllm","name":"vLLM project","country":"unknown","parent":null,"kind":"community","url":"https://vllm.ai","european":"unknown"},"needs":["ai-models"],"replaces":["openai-api"],"offerings":[{"mode":"self-host","price":{"basis":"free"}}],"resources":{"ram_mb":8192,"cpu":4,"disk_gb":50,"basis":"needs a GPU server"},"ash":null,"kind":"software","provenance":{"source":"curated","verified":"2026-09-04"},"open_source":true,"data_classes":["intellectual-property"],"modes":["sh"],"verdicts":{"sh":{"verdict":"green","rule":1,"reason":"You run it yourself: no data leaves your own infrastructure."}},"upstream":null,"needs_expanded":[{"id":"ai-models","name":"AI models","data_classes":["intellectual-property"]}],"page":"/tools/vllm"}