How to use /detect /point with VLLM API

[dhandhalyabhavik]

If I use VLLM based docker and expose moondream via OpenAI APIs, then how to use /detect or /point? OpenAI doesn't support those APIs right?

# Call the server using curl:
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vikhyatk/moondream2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

[AlexisMDP]

Moondream does not work on vLLM.