{
 "schema_version": 1,
 "generated": "2026-10-23",
 "repo": "vllm-project/vllm",
 "name": "vllm",
 "owner": "vllm-project",
 "slug": "vllm-project-vllm",
 "github": "https://github.com/vllm-project/vllm",
 "what": "vLLM is a fast, easy-to-use library for LLM inference and serving, with an OpenAI-compatible API server.",
 "why": "+1,327 stars this week, 95k total, picked up by one AI source we track",
 "language": "Python",
 "requirements": [
  "Python with uv or pip installed",
  "A supported NVIDIA, AMD or Intel GPU, or an x86, ARM or PowerPC CPU",
  "A Hugging Face model you are allowed to download and use"
 ],
 "audience_note": "Built for engineers and ML teams who need to run open-weight language models on their own GPUs or CPUs at high throughput.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/vllm-project-vllm/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "vllm-project-vllm--serve-open-llm-openai-compatible-api",
   "title": "Serve an open LLM behind an OpenAI-compatible API",
   "best": true,
   "url": "https://dedupedai.com/use-cases/vllm-project-vllm/serve-open-llm-openai-compatible-api/",
   "json": "https://dedupedai.com/use-cases/u/vllm-project-vllm/serve-open-llm-openai-compatible-api.json"
  },
  {
   "id": "vllm-project-vllm--generate-structured-json-outputs",
   "title": "Get structured JSON output from a self-hosted model",
   "best": false,
   "url": "https://dedupedai.com/use-cases/vllm-project-vllm/generate-structured-json-outputs/",
   "json": "https://dedupedai.com/use-cases/u/vllm-project-vllm/generate-structured-json-outputs.json"
  },
  {
   "id": "vllm-project-vllm--serve-lora-adapters-from-one-base-model",
   "title": "Serve several LoRA fine-tunes from one base model",
   "best": false,
   "url": "https://dedupedai.com/use-cases/vllm-project-vllm/serve-lora-adapters-from-one-base-model/",
   "json": "https://dedupedai.com/use-cases/u/vllm-project-vllm/serve-lora-adapters-from-one-base-model.json"
  },
  {
   "id": "vllm-project-vllm--create-text-embeddings-with-served-models",
   "title": "Create text embeddings from a served retrieval model",
   "best": false,
   "url": "https://dedupedai.com/use-cases/vllm-project-vllm/create-text-embeddings-with-served-models/",
   "json": "https://dedupedai.com/use-cases/u/vllm-project-vllm/create-text-embeddings-with-served-models.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}