Basic Agent

Run a basic agent against a local vLLM server.

Code

vllm_basic.py

from agno.agent import Agent
from agno.models.vllm import VLLM

agent = Agent(
    model=VLLM(id="Qwen/Qwen2.5-7B-Instruct", top_k=20, enable_thinking=False),
    markdown=True,
)

agent.print_response("Share a 2 sentence horror story")

Install vLLM on a supported platform with a compatible accelerator. Keep the model server running in a separate terminal while you run the agent.

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno openai vllm
   
3. Start vLLM server

   In a separate terminal with the virtual environment active, run:

   vllm serve Qwen/Qwen2.5-7B-Instruct \
       --enable-auto-tool-choice \
       --tool-call-parser hermes \
       --dtype float16 \
       --max-model-len 8192 \
       --gpu-memory-utilization 0.9
   
4. Set your API key

   export VLLM_API_KEY=xxx
   
5. Run Agent

   Save the code above as vllm_basic.py, then run:

   python vllm_basic.py