{
  "slug": "vllm",
  "name": "vLLM",
  "company": "vLLM Project",
  "website": "https://docs.vllm.ai",
  "category": "platforms",
  "business_model": "open",
  "availability": "global",
  "launched": "2023",
  "tags": [
    "open-source",
    "inference",
    "serving",
    "llm"
  ],
  "description": "Open-source inference and serving engine for large language models, known for high-throughput PagedAttention.",
  "i18n": {
    "zh": {
      "description": "面向大语言模型的开源推理与服务引擎，以高吞吐的 PagedAttention 而知名。"
    },
    "es": {
      "description": "Motor de inferencia y servicio de código abierto para grandes modelos de lenguaje, conocido por su PagedAttention de alto rendimiento."
    },
    "fr": {
      "description": "Moteur d'inférence et de service open source pour grands modèles de langue, connu pour son PagedAttention à haut débit."
    },
    "ja": {
      "description": "大規模言語モデル向けのオープンソース推論・サービングエンジン。高スループットの PagedAttention で知られる。"
    },
    "de": {
      "description": "Quelloffene Inferenz- und Serving-Engine für große Sprachmodelle, bekannt für das durchsatzstarke PagedAttention."
    },
    "pt": {
      "description": "Motor de inferência e serving de código aberto para grandes modelos de linguagem, conhecido pelo PagedAttention de alto rendimento."
    },
    "ko": {
      "description": "대규모 언어 모델을 위한 오픈 소스 추론·서빙 엔진으로, 높은 처리량의 PagedAttention으로 알려져 있다."
    }
  },
  "sources": [
    {
      "title": "Documentation",
      "url": "https://docs.vllm.ai"
    },
    {
      "title": "Source code (GitHub)",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "updated": "2026-07-24",
  "url": "https://globalaiproductindex.com/products/vllm/"
}