Runpod•14mo ago

"Failed to return job results. | Connection timeout to host https://api.runpod.ai/v2/91gr..."

I keep having these errors on my endpoints.

It happens most of the time for "high-res" images (4K) but they're JPEG and max 2MB.

Runpod serverless pods have significantly deteriorated these last days for me.

Nikita•11/20/24, 10:52 AM

What is your SDK version?

sidouOP•11/20/24, 11:07 AM

Thanks for your help. Do you know where I can find this info?

sidouOP•11/20/24, 11:08 AM

(Note: I just noticed this happened with A100 PCIe and NOT A100 SXM)

Nikita•11/20/24, 11:13 AM

info about the SDK version is usually in your dockerfile or requirements.txt of your repository

sidouOP•11/20/24, 11:15 AM

I put this in my dockerfile -> So I guess it's the latest version of runpod

RUN /opt/venv/bin/pip install runpodRUN /opt/venv/bin/pip install runpod

Nikita•11/20/24, 11:41 AM

and i assume the code is fine as you have workers that are okay
when did you deploy on your a100 pcie for the last time? I guess it might be related to the recent price drop for bigger GPUs followed by availability decrease

Nikita•11/20/24, 11:42 AM

or it might be related to volume attached to it

Nikita•11/20/24, 11:44 AM

anyway if your images doesnt exceed the limit of 10 mbs of a payload and it works on some machines, i would suggest you to try redeploying it :\

Nikita•11/20/24, 11:44 AM

I've noticed that some of my A6000/A40 workers have been falling into throttling mode very often lately

"Failed to return job results. | Connection timeout to host https://api.runpod.ai/v2/91gr..."

Similar Threads

Similar Threads

Similar Threads