How to Deploy InternVL3-8B with vLLM

# Setup
python3.12 -m venv venv && source venv/bin/activate
pip install --upgrade pip && pip install vllm

# Launch
vllm serve OpenGVLab/InternVL3-8B \
  --trust-remote-code \
  --dtype bfloat16 \
  --max-model-len 32768 \
  --max-num-batched-tokens 32768 \
  --gpu-memory-utilization 0.9 \
  --port 8000

# Test
curl http://localhost:8000/v1/models

VIDEO_BASE64=$(base64 -w 0 /path/to/video.mp4)
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d "{
    \"model\": \"OpenGVLab/InternVL3-8B\",
    \"messages\": [{
      \"role\": \"user\",
      \"content\": [
        {\"type\": \"video_url\", \"video_url\": {\"url\": \"data:video/mp4;base64,\$VIDEO_BASE64\"}},
        {\"type\": \"text\", \"text\": \"Describe this video.\"}
      ]
    }],
    \"max_tokens\": 1024
  }"