{
  "id": 599966,
  "title": "Submission issue: does notebook need to run under 900s?",
  "url": "/competitions/cmi-detect-behavior-with-sensor-data/discussion/599966",
  "author_name": "",
  "post_date": "2025-08-20T07:01:55.273361300Z",
  "votes": null,
  "comment_count": 4,
  "views": 0,
  "content": "<p>I have a doubt about whether the notebook is supposed to run within 900 seconds. When I try to submit it, the inference server never starts. Has anyone else faced this issue, or is there something I might be missing?</p>",
  "messages": [
    {
      "id": "3272045",
      "postDate": "08/20/2025 07:01:55",
      "content": "<p>I have a doubt about whether the notebook is supposed to run within 900 seconds. When I try to submit it, the inference server never starts. Has anyone else faced this issue, or is there something I might be missing?</p>",
      "rawMarkdown": "I have a doubt about whether the notebook is supposed to run within 900 seconds. When I try to submit it, the inference server never starts. Has anyone else faced this issue, or is there something I might be missing?",
      "votes": null
    },
    {
      "id": "3272445",
      "postDate": "08/21/2025 01:01:57",
      "content": "<p>Yes – if the inference server doesn’t start within ~900 s, the submission fails. Make sure the server starts quickly:</p>\n<p>Don’t run heavy preprocessing or downloads before <code>inference_server.run()</code>.</p>\n<p>Load models/files only from <code>/kaggle/input.</code></p>\n<p>Test locally with <code>run_local_gateway</code> to ensure startup is fast (&lt;1 min).</p>",
      "rawMarkdown": "Yes – if the inference server doesn’t start within ~900 s, the submission fails. Make sure the server starts quickly:\n\nDon’t run heavy preprocessing or downloads before `inference_server.run()`.\n\nLoad models/files only from `/kaggle/input.`\n\nTest locally with `run_local_gateway` to ensure startup is fast (<1 min).",
      "votes": null
    },
    {
      "id": "3272475",
      "postDate": "08/21/2025 03:12:41",
      "content": "<p>How to solve Gateway Runtime Error?<br>\nmodel loaded successfully and <code>inference_server.run()</code> but inference server did not run…</p>\n<p>Notebook Inference Server Error:<br>\nYour submission notebook did not register the expected endpoint to your inference server.</p>\n<pre><code>---------------------------------------------------------------------------\nGatewayRuntimeError                       Traceback (most recent call last)\n/tmp/ipykernel_36/  &lt;cell : &gt;()\n           inference_server()\n       :\n----&gt;      inference_server(\n               data_paths=(\n                   ,\n...\nGatewayRuntimeError: (&lt;GatewayRuntimeErrorType: &gt;, )\n</code></pre>",
      "rawMarkdown": "How to solve Gateway Runtime Error?\nmodel loaded successfully and `inference_server.run()` but inference server did not run...\n\nNotebook Inference Server Error:\nYour submission notebook did not register the expected endpoint to your inference server.\n```\n---------------------------------------------------------------------------\nGatewayRuntimeError                       Traceback (most recent call last)\n/tmp/ipykernel_36/1232577806.py in <cell line: 0>()\n      5     inference_server.serve()\n      6 else:\n----> 7     inference_server.run_local_gateway(\n      8         data_paths=(\n      9             '/kaggle/input/cmi-detect-behavior-with-sensor-data/test.csv',\n...\nGatewayRuntimeError: (<GatewayRuntimeErrorType.SERVER_MISSING_ENDPOINT: 4>, 'Server did not register a listener for predict')\n```",
      "votes": null
    },
    {
      "id": "3272482",
      "postDate": "08/21/2025 04:02:34",
      "content": "<p>Thanks for the information!!!</p>",
      "rawMarkdown": "Thanks for the information!!!",
      "votes": null
    },
    {
      "id": "3272591",
      "postDate": "08/21/2025 09:31:05",
      "content": "<p>you need to do a prediction function that must be named 'predict' similar to public notebooks</p>\n<p>from the  error message looks like you don't have a function named predict</p>",
      "rawMarkdown": "you need to do a prediction function that must be named 'predict' similar to public notebooks\n\nfrom the  error message looks like you don't have a function named predict",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3272445,
      "author_name": "harutokotou",
      "author_url": "",
      "post_date": "08/21/2025 01:01:57",
      "content": "<p>Yes – if the inference server doesn’t start within ~900 s, the submission fails. Make sure the server starts quickly:</p>\n<p>Don’t run heavy preprocessing or downloads before <code>inference_server.run()</code>.</p>\n<p>Load models/files only from <code>/kaggle/input.</code></p>\n<p>Test locally with <code>run_local_gateway</code> to ensure startup is fast (&lt;1 min).</p>",
      "votes": null,
      "replies": [
        {
          "id": 3272475,
          "author_name": "ikarus99",
          "author_url": "",
          "post_date": "08/21/2025 03:12:41",
          "content": "<p>How to solve Gateway Runtime Error?<br>\nmodel loaded successfully and <code>inference_server.run()</code> but inference server did not run…</p>\n<p>Notebook Inference Server Error:<br>\nYour submission notebook did not register the expected endpoint to your inference server.</p>\n<pre><code>---------------------------------------------------------------------------\nGatewayRuntimeError                       Traceback (most recent call last)\n/tmp/ipykernel_36/  &lt;cell : &gt;()\n           inference_server()\n       :\n----&gt;      inference_server(\n               data_paths=(\n                   ,\n...\nGatewayRuntimeError: (&lt;GatewayRuntimeErrorType: &gt;, )\n</code></pre>",
          "votes": null,
          "replies": [
            {
              "id": 3272591,
              "author_name": "tahaalshatiri",
              "author_url": "",
              "post_date": "08/21/2025 09:31:05",
              "content": "<p>you need to do a prediction function that must be named 'predict' similar to public notebooks</p>\n<p>from the  error message looks like you don't have a function named predict</p>",
              "votes": null,
              "replies": []
            }
          ]
        },
        {
          "id": 3272482,
          "author_name": "roxhap",
          "author_url": "",
          "post_date": "08/21/2025 04:02:34",
          "content": "<p>Thanks for the information!!!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "3272045": "I have a doubt about whether the notebook is supposed to run within 900 seconds. When I try to submit it, the inference server never starts. Has anyone else faced this issue, or is there something I might be missing?",
    "3272445": "Yes – if the inference server doesn’t start within ~900 s, the submission fails. Make sure the server starts quickly:\n\nDon’t run heavy preprocessing or downloads before `inference_server.run()`.\n\nLoad models/files only from `/kaggle/input.`\n\nTest locally with `run_local_gateway` to ensure startup is fast (<1 min).",
    "3272475": "How to solve Gateway Runtime Error?\nmodel loaded successfully and `inference_server.run()` but inference server did not run...\n\nNotebook Inference Server Error:\nYour submission notebook did not register the expected endpoint to your inference server.\n```\n---------------------------------------------------------------------------\nGatewayRuntimeError                       Traceback (most recent call last)\n/tmp/ipykernel_36/1232577806.py in <cell line: 0>()\n      5     inference_server.serve()\n      6 else:\n----> 7     inference_server.run_local_gateway(\n      8         data_paths=(\n      9             '/kaggle/input/cmi-detect-behavior-with-sensor-data/test.csv',\n...\nGatewayRuntimeError: (<GatewayRuntimeErrorType.SERVER_MISSING_ENDPOINT: 4>, 'Server did not register a listener for predict')\n```",
    "3272482": "Thanks for the information!!!",
    "3272591": "you need to do a prediction function that must be named 'predict' similar to public notebooks\n\nfrom the  error message looks like you don't have a function named predict"
  },
  "source": "meta"
}