CapRL-Qwen3VL-4B

vllm serve "/PATH/CapRL-3B" \
    --trust-remote-code \
    --tensor-parallel-size=1 \
    --pipeline-parallel-size=1 \
    --gpu_memory_utilization=0.95 \
    --served-model-name=caprl \
    --port 8000 \
    --host 0.0.0.0

import base64
from openai import OpenAI
# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)
image_path = "/path/to/local/image.png"
with open(image_path, "rb") as f:
    encoded_image = base64.b64encode(f.read())
encoded_image_text = encoded_image.decode("utf-8")
base64_qwen = f"data:image;base64,{encoded_image_text}"
chat_response = client.chat.completions.create(
    model="caprl",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": base64_qwen
                    },
                },
                {"type": "text", "text": "What is the text in the illustrate?"},
            ],
        },
    ],
    temperature=1.0,
    max_tokens=max_tokens,
    top_p=1.0,
    extra_body={
        "repetition_penalty": 1.0,
        },
)
print("Chat response:", chat_response)