{
  "schemaVersion": "1.0",
  "updates": [],
  "companyNews": [],
  "id": "b635",
  "language": "en",
  "name": "SGLang",
  "originalName": "SGLang",
  "library": "tools",
  "category": "Model development",
  "categoryKey": "模型开发",
  "categoryKeys": [
    "模型开发"
  ],
  "categories": [
    "Model development"
  ],
  "entryPoints": [],
  "summary": "Inference framework for language and multimodal models, with prefix caching and multi-device serving.",
  "introduction": "SGLang is an open-source inference framework hosted by LMSYS for language, vision-language and other models. Install a runtime, load weights and launch a server, then send generation, streaming or tool-calling requests from applications. RadixAttention and prefix caching reuse shared context, while multi-GPU parallelism scales serving. The repository also contains SGLang Diffusion for image and video generation. Check current model, hardware and API compatibility lists.",
  "capabilities": [],
  "company": {
    "name": "LMSYS",
    "originalName": "LMSYS"
  },
  "officialUrl": "https://docs.sglang.io/",
  "profileUpdatedOn": "2026-10-22",
  "sources": [
    {
      "kind": "product",
      "url": "https://docs.sglang.io/"
    }
  ],
  "news": [],
  "links": {
    "interactive": "products/sglang--b635.html",
    "reading": "read/en/products/sglang--b635.html",
    "markdown": "read/en/products/sglang--b635.md",
    "json": "read/en/products/sglang--b635.json"
  }
}