My setup is as follows: I deployed Qwen3.5-9B-AWQ locally using VLLM and used litellm as the aggregator.

My litellm --config litellm_config.yaml configuration is as follows:

general_settings: host: 0.0.0.0 port: 4000 debug: true master_key: "123456" model_list: - model_name: "Qwen3.5-9B-AWQ" litellm_params: model: "openai/Qwen3.5-9B-AWQ" api_base: "http://10.1.1.128:8000/v1" api_key: "123"

- model_name: "Qwen3.5-9B-AWQ" litellm_params: model: "openai/Qwen3.5-9B-AWQ" api_base: "http://10.1.1.128:8001/v1" api_key: "123"

I want the same model alias (e.g., "Qwen3.5-9B-AWQ") to be callable by both /chat/completions and /v1/messages.

How do I modify the configuration?

Using the model configuration `model: "openai/Qwen3.5-9B-AWQ"` results in errors when calling the interface via an agent, and normal conversation is not possible. Attempting to use `model: "anthropic/Qwen3.5-9B-AWQ"` causes the litellm process to hang, as well as the backend vLLM process to hang.