Strange results in Serverless mode
What Am I doing wrong?
Why the response is that strange?
I've attached the input params and one of the result....
Serverless Endpoint using official github repo Stuck at "Waiting for building"
Hi, I'm deploying a serverless endpoint using the official github repo runpod-workers/worker-template. I just fork this repo and add one line in dockerfile "RUN pip install --upgrade pip && pip install uv" WITHOUT any other changes.
Build completes successfully with no errors in the logs. However, during the testing phase, the status remains at "Waiting for building" indefinitely. No test logs are generated. After about an hour, the process cancels automatically.
I've tried increasing the max workers to 2 and allowing multiple GPU types, but the issue persists. Could someone assist me in identifying what's causing the worker to hang during initialization?...
Some query take a long time than usual
I notice that some query take very long time (stucking in delay), why ?
Ps. I notice thar problem occur when I leave server idle for a while...
The total token limit at 131
I use vLLM and set max model length to 8000 a2048 but out is just 131 (total out + in ), although i have set max tokens to 2048. I try with 2 models and result is the same.
failing to start job
One of 10 times we are getting error message when trying to pass message. The error is no inside serverless container. Job is not getting processed by runpod itself.
running from fastapi background_task. Sot the trace is not full
```...
Serverless TimeoutError: "Failed to get job"
Issue:
Getting repeated
- Error:
- Happens even with 120s timeout, single request takes at max 20 sec. Configuration: ...
Getting repeated
TimeoutError in RunPod Serverless with no clear cause (no GPU OOM or other errors).- Error:
Failed to get job. | Error Type: TimeoutError | Error Message: Runpod serverless- Happens even with 120s timeout, single request takes at max 20 sec. Configuration: ...
