> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mem0.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# vLLM

> Configure vLLM as an LLM provider in Mem0 for high-performance local inference with GPU-optimized serving.

[vLLM](https://docs.vllm.ai/) is a high-performance inference engine for large language models that provides significant performance improvements for local inference. It's designed to maximize throughput and memory efficiency for serving LLMs.

## Prerequisites

1. **Install vLLM**:

   ```bash theme={null}
   pip install vllm
   ```

2. **Start vLLM server**:

   ```bash theme={null}
   # For testing with a small model
   vllm serve microsoft/DialoGPT-medium --port 8000

   # For production with a larger model (requires GPU)
   vllm serve Qwen/Qwen2.5-32B-Instruct --port 8000
   ```

## Usage

<CodeGroup>
  ```python Python theme={null}
  import os
  from mem0 import Memory

  os.environ["OPENAI_API_KEY"] = "your-api-key"  # used for embedding model

  config = {
      "llm": {
          "provider": "vllm",
          "config": {
              "model": "Qwen/Qwen2.5-32B-Instruct",
              "vllm_base_url": "http://localhost:8000/v1",
              "temperature": 0.1,
              "max_tokens": 2000,
          }
      }
  }

  m = Memory.from_config(config)
  messages = [
      {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
      {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
      {"role": "user", "content": "I'm not a big fan of thrillers, but I love sci-fi movies."},
      {"role": "assistant", "content": "Got it! I'll avoid thrillers and suggest sci-fi movies instead."}
  ]
  m.add(messages, user_id="alice", metadata={"category": "movies"})
  ```

  ```typescript TypeScript theme={null}
  import { Memory } from "mem0ai/oss";

  const config = {
    llm: {
      provider: "vllm",
      config: {
        model: "Qwen/Qwen2.5-32B-Instruct",
        baseURL: "http://localhost:8000/v1",
        apiKey: process.env.VLLM_API_KEY || "vllm-api-key",
        temperature: 0.1,
        maxTokens: 2000,
      },
    },
  };

  const memory = new Memory(config);
  const messages = [
    {
      role: "user",
      content: "I'm planning to watch a movie tonight. Any recommendations?",
    },
    {
      role: "assistant",
      content: "How about thriller movies? They can be quite engaging.",
    },
    {
      role: "user",
      content: "I'm not a big fan of thrillers, but I love sci-fi movies.",
    },
    {
      role: "assistant",
      content: "Got it! I'll avoid thrillers and suggest sci-fi movies instead.",
    },
  ];
  await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
  ```
</CodeGroup>

## Configuration Parameters

| Parameter       | Description                       | Default                       | Environment Variable |
| --------------- | --------------------------------- | ----------------------------- | -------------------- |
| `model`         | Model name running on vLLM server | `"Qwen/Qwen2.5-32B-Instruct"` | -                    |
| `vllm_base_url` | vLLM server URL                   | `"http://localhost:8000/v1"`  | `VLLM_BASE_URL`      |
| `api_key`       | API key (dummy for local)         | `"vllm-api-key"`              | `VLLM_API_KEY`       |
| `temperature`   | Sampling temperature              | `0.1`                         | -                    |
| `max_tokens`    | Maximum tokens to generate        | `2000`                        | -                    |

## Environment Variables

You can set these environment variables instead of specifying them in config:

```bash theme={null}
export VLLM_BASE_URL="http://localhost:8000/v1"
export VLLM_API_KEY="your-vllm-api-key"
export OPENAI_API_KEY="your-openai-api-key"  # for embeddings
```

## Benefits

* **High Performance**: 2-24x faster inference than standard implementations
* **Memory Efficient**: Optimized memory usage with PagedAttention
* **Local Deployment**: Keep your data private and reduce API costs
* **Easy Integration**: Drop-in replacement for other LLM providers
* **Flexible**: Works with any model supported by vLLM

## Troubleshooting

1. **Server not responding**: Make sure vLLM server is running

   ```bash theme={null}
   curl http://localhost:8000/health
   ```

2. **404 errors**: Ensure correct base URL format

   ```python theme={null}
   "vllm_base_url": "http://localhost:8000/v1"  # Note the /v1
   ```

3. **Model not found**: Check model name matches server

4. **Out of memory**: Try smaller models or reduce `max_model_len`

   ```bash theme={null}
   vllm serve Qwen/Qwen2.5-32B-Instruct --max-model-len 4096
   ```

## Config

All available parameters for the `vllm` config are present in [Master List of All Params in Config](../config).