{
 "schema_version": 1,
 "generated": "2026-10-25",
 "id": "sgl-project-sglang--serve-an-open-model-on-your-own-gpus",
 "repo": "sgl-project/sglang",
 "repo_url": "https://github.com/sgl-project/sglang",
 "repo_slug": "sgl-project-sglang",
 "title": "Serve an open model on your own GPUs",
 "page_title": "How to serve an open model on your own GPUs with SGLang",
 "summary": "Install SGLang, pick a ready-to-run launch command for your model and hardware, and send a first request.",
 "who": "A team moving from a paid API to self-hosted open models.",
 "problem": "API bills grow with usage, and some data cannot leave your servers.",
 "outcome": "An SGLang server running your chosen model, answering requests on your hardware.",
 "steps": [
  "Pull the image: `docker pull lmsysorg/sglang:latest`, or install with `uv pip install --prerelease=allow sglang`",
  "Open the Cookbook and choose your model and hardware to get a launch command",
  "Launch the model and follow the Quickstart to send your first request",
  "Check the hardware platform guide for your GPU before tuning"
 ],
 "agent_prompt": "Set up sgl-project/sglang with Docker on this <GPU> machine, use the Cookbook launch command for <model>, send one test request, and report tokens per second.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "Large models need large GPUs; check the Cookbook's hardware notes for your model first.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "A supported GPU or accelerator (NVIDIA, AMD, TPU and others)",
  "Docker, or a Python environment with uv"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/sgl-project-sglang/serve-an-open-model-on-your-own-gpus/",
 "md": "https://dedupedai.com/use-cases/sgl-project-sglang/serve-an-open-model-on-your-own-gpus/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/sgl-project-sglang--serve-an-open-model-on-your-own-gpus.json",
 "api_version": "v1"
}