vLLM

vLLM is a fast and easy-to-use library for LLM inference and serving, designed for high-throughput and memory-efficient LLM serving.

Prerequisites

Install vLLM and start serving a model:

install vLLM

uv pip install vllm

start vLLM server

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

This spins up the vLLM server with an OpenAI-compatible API.

The default vLLM server URL is http://localhost:8000/

Example

Basic Agent

agent.py

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

agent = Agent(
    model=VLLM(
        id="meta-llama/Llama-3.1-8B-Instruct",
        base_url="http://localhost:8000/",
    ),
    markdown=True
)

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

Advanced Usage

With Tools

vLLM models work seamlessly with Agno tools:

with_tools.py

from agno.agent import Agent
from agno.models.vllm import VLLM
from agno.tools.hackernews import HackerNewsTools

agent = Agent(
    model=VLLM(id="meta-llama/Llama-3.1-8B-Instruct"),
    tools=[HackerNewsTools()],
    markdown=True
)

agent.print_response("What's the latest news about AI?")

View more examples here.

For the full list of supported models, see the vLLM documentation.

Params

Parameter	Type	Default	Description
id	str	"microsoft/DialoGPT-medium"	The id of the model to use with vLLM
name	str	"vLLM"	The name of the model
provider	str	"vLLM"	The provider of the model
api_key	Optional[str]	None	The API key (usually not needed for local vLLM)
base_url	str	"http://localhost:8000/v1"	The base URL for the vLLM server

VLLM is a subclass of the Model class and has access to the same params.