rednote-hilab

/

dots.vlm1.inst

like 80

Follow

rednote-hilab 553

docker run -it --gpus all rednotehilab/dots.vlm1_sglang:v0.4.9.post1-cu126
I use the folloing command to start a server successfully:
python -m sglang.launch_server --model-path /workspace/models/dots.vlm1.inst/ --tp-size 8

The pure text requests work fine but it goes wrong with requests containing images.

curl http://127.0.0.1:30000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dots.vlm1.inst",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "请描述下面的图片"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 300
  }'

The reply shows that the image is not processed or understood by the model.
I found that something might went wrong with the chat template. Can you please check this?