> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# vLLM

> vLLM is a fast and easy-to-use library for running LLM models locally.

| Example | Description |
| - | - |
| [vLLM Basic](https://agno-v2.mintlify.site/examples/models/vllm/basic.md) | Run a Qwen2.5-7B agent on a local vLLM server in sync, async, and streaming modes. |
| [Code Generation](https://agno-v2.mintlify.site/examples/models/vllm/code-generation.md) | Code generation example with DeepSeek-Coder. |
| [DB](https://agno-v2.mintlify.site/examples/models/vllm/db.md) | Store a vLLM agent's session history in Postgres and reuse it across turns. |
| [Memory](https://agno-v2.mintlify.site/examples/models/vllm/memory.md) | Personalized memory and session summaries with vLLM. |
| [Retry](https://agno-v2.mintlify.site/examples/models/vllm/retry.md) | Review retry settings and why invalid model IDs cannot reliably exercise the retry path. |
| [vLLM Structured Output](https://agno-v2.mintlify.site/examples/models/vllm/structured-output.md) | Return a typed MovieScript object from a vLLM agent with a Pydantic output schema. |
| [vLLM Tool Use](https://agno-v2.mintlify.site/examples/models/vllm/tool-use.md) | Build a web search agent using vLLM. |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.