letta-server/tests/configs/llm_model_configs/vllm.json

{
  "context_window": 8192,
  "model_endpoint_type": "vllm",
  "model_endpoint": "http://127.0.0.1:8000",
  "model": "Qwen/Qwen3-32B-AWQ",
  "put_inner_thoughts_in_kwargs": true
}