serverless error
I'm facing an error while using RunPod, and I could use some help figuring out what might be going wrong. Below is the error I received:
{
"endpointId": "98pu6z4wg5srca",
"workerId": "mxwusxazi52e45",
"level": "error",
"message": "{"trace_id": "affdfee6-4ec3-4dce-bd4f-fd785cd7d398", "request_id": "sync-ded15fc4-0e6b-4e8d-b8db-df6dd897cd0c-e1", "user_agent": "RunPod-Python-SDK/1.7.0 (Linux 5.4.0-167-generic; x86_64) Language/Python 3.10.12", "start_time": "2024-09-27T18:52:32.246452+00:00", "method": "GET", "url": "https://api.runpod.ai/v2/98pu6z4wg5srca/job-take/mxwusxazi52e45?gpu=NVIDIA H100 80GB HBM3&job_in_progress=0", "mode": "async", "connect": 1.6, "payload_size_bytes": 0, "exception": "", "transfer": 3140592.9, "end_time": "2024-09-27T19:44:52.841015+00:00", "total": 3140594.6}",
"dt": "2024-09-27 19:44:52.84539616"
}
As you can see, the transfer and total time are extremely long (about 36 days). It seems like the connection is established (connect: 1.6 seconds), but the request doesn’t complete, and there’s no specific error message (exception is empty).
Has anyone else experienced something like this, or does anyone have an idea about what could be causing it? Any help or insights would be greatly appreciated!
Thanks in advance!
2 Replies
What is your worker doing? Is it trying to download model or something?
any news on this, i got the same problem?