{
  "schemaVersion": "1.0",
  "updates": [
    {
      "id": "official-release-b634-20261018",
      "importance": "changelog",
      "product": "vLLM",
      "title": "vLLM releases v0.32.0",
      "summary": "Adds structured decisions, generic parsers and broader low-precision KV caches, with model- and hardware-specific requirements.",
      "originalPublishedOn": "2026-10-18",
      "source": "vLLM",
      "sourceUrl": "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
    }
  ],
  "companyNews": [],
  "id": "b634",
  "language": "en",
  "name": "vLLM",
  "originalName": "vLLM",
  "library": "tools",
  "category": "Model development",
  "categoryKey": "模型开发",
  "categoryKeys": [
    "模型开发"
  ],
  "categories": [
    "Model development"
  ],
  "entryPoints": [],
  "summary": "Serve language models with KV-cache management, continuous batching, quantization and multi-device parallelism.",
  "introduction": "vLLM is an open-source engine for language-model inference and serving. Configure a model and hardware to generate in batches or run an API server for application requests. PagedAttention, continuous batching and prefix caching manage inference memory and scheduling; quantization, structured outputs and distributed inference are also supported. It does not supply model weights or hosted compute. Compatibility and performance depend on the model, backend and configuration.",
  "capabilities": [],
  "company": {
    "name": "vLLM Project",
    "originalName": "vLLM Project"
  },
  "officialUrl": "https://docs.vllm.ai/en/latest/",
  "profileUpdatedOn": "2026-10-22",
  "sources": [
    {
      "kind": "product",
      "url": "https://docs.vllm.ai/en/latest/"
    }
  ],
  "news": [],
  "links": {
    "interactive": "products/vllm--b634.html",
    "reading": "read/en/products/vllm--b634.html",
    "markdown": "read/en/products/vllm--b634.md",
    "json": "read/en/products/vllm--b634.json"
  }
}