Add vision id for Qwen3-VL

[CUHKSZzxy]

Motivation

For multiple visual inputs, Qwen3-VL should be able to add index for each input automatically, via its chat template.
The prompt would be formatted like Picture1 xxx, Picture2 xxx, ... Picture n.
As claimed, it may improve multi-image benchmarking.

https://github.com/QwenLM/Qwen3-VL?tab=readme-ov-file#add-ids-for-multiple-visual-inputs

Usage

User can add vision id by adding "add_vision_id": true in the message, as follows:

curl http://0.0.0.0:23333/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-VL-8B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Can you describe these images?"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg"
                    }
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
                    }
                }
            ]
        }
    ],
    "add_vision_id": true
  }'