Problem use vllm load qwen3

General
1

from agno.agent import Agent

from agno.models.vllm import VLLM

agent = Agent(

***model*****=VLLM(*id*="qwen3", *base_url*="http://localhost:9999/v1/", *enable_thinking*=False),**

***markdown*****=True,**

)

agent.print_response(“Share a 2 sentence horror story”)

Response is null

wechat_2025-10-22_151036_502
wechat_2025-10-22_151036_5021540×285 6.49 KB

2

Hi @skenoy, thanks for reaching out and supporting Agno. I’ve shared this with the team, we’re working through all requests one by one and will get back to you soon.If it’s urgent, please let us know. We appreciate your patience!

3

Hey @skenoy

We will need some more information to help you debug this.

  • You can add debug_mode=True to the Agent so we can see more logs
  • How are your running your qwen3 model? Are we sure it is working, when used without Agno?