How to run SAM3 on Roboflow Inference on Jetson

[zhiweit]

Search before asking

• I have searched the Inference issues and found no similar feature requests.

Question

How to run SAM3 locally on jetson using roboflow inference?

I am running roboflow inference server on my jetson orin device using docker image as per the installation instructions using jetpack 6.2.0

I would like to run SAM3 locally on the roboflow inference server running on the jetson.
I was following the guide here and tried running the curl command

curl -X POST 'http://localhost:9001/sam3/concept_segment?api_key=<YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
    "image": {
      "type": "url",
      "value": "https://media.roboflow.com/inference/sample.jpg"
    },
    "prompts": [
        { "type": "text", "text": "cat" },
        { "type": "text", "text": "dog" }
    ]
  }'

but i got

{"message":"Service misconfiguration."}% 

May I ask how to run SAM3 model locally on the roboflow inference server and how to use roboflow inference http client to call it? I would greatly appreciate any help / guide on this!

Additional

No response