1

I deploy Llama 3.1 Nemotron Nano 8B V1 from AWS Marketplace by AWS CloudFormation Template to SageMaker Endpoint. But during the deployment, getting errors:

RuntimeError: The NVIDIA driver on your system is too old (found version 11040). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.

{
    "level": "error",
    "ts": 1749737718.189629,
    "logger": "http.log.error.default",
    "msg": "dial tcp 127.0.0.1:8000: connect: connection refused",
    "request": {
        "remote_ip": "169.254.178.2",
        "remote_port": "47138",
        "client_ip": "169.254.178.2",
        "proto": "HTTP/1.1",
        "method": "GET",
        "host": "169.254.180.2:8080",
        "uri": "/ping",
        "headers": {
            "Accept": [
                "*/*"
            ],
            "User-Agent": [
                "AHC/2.0"
            ]
        }
    },
    "duration": 0.000249412,
    "status": 502,
    "err_id": "gzsu5hrw1",
    "err_trace": "reverseproxy.statusError (reverseproxy.go:1373)"
}