worker no execute | Runpod | Page 1

cerulean marlin Jun 25, 2024, 2:20 PM

#

this worker "ir6fwdhb34ujm7" run but no execute, why????

#

worker no execute

hardy falcon Jun 25, 2024, 2:24 PM

#

What does "no execute" mean?
What do the logs say?

cerulean marlin Jun 25, 2024, 2:34 PM

#

#

The 1st one executed nothing I canceled it manually, the 2nd one canceled it after a timeout and it looks like it was not assigned to a GPU

void yew Jun 25, 2024, 2:44 PM

#

Where is the message that made it look like it was not assigned to a gpu?

#

Copy texts, not screenshots please

cerulean marlin Jun 25, 2024, 2:48 PM

#

📎 test

void yew Jun 25, 2024, 3:02 PM

#

whats your base docker image?

#

is that the full logs? yeah i see no "cuda" or "pytorch" signs meaning the gpu can be not loaded

cerulean marlin Jun 25, 2024, 3:13 PM

#

Here's the full log, docker image templates id 98y63mu2ic, multiple wokers are allowed at the same time and only this worker has problems

void yew Jun 25, 2024, 4:02 PM

#

Try to contact support via the website with your endpoint id

#

contact button on the left

hardy falcon Jun 25, 2024, 4:02 PM

#

Its probably issue with the worker itself, not a RunPod issue

#

I would log a Github isssue on the repo you're using before contacting RunPod support

cerulean marlin Jun 25, 2024, 4:52 PM

#

Is the process that complicated? I've promoted runpod to countless people before because I thought it had prompt customer service, but why is the process so complicated

void yew Jun 25, 2024, 5:06 PM

#

It could be many possibility thats causing that issue, best to check workers code too but the way the current way of contacting official staffs is my email or ticket

hardy falcon Jun 25, 2024, 5:09 PM

#

Its definitely the worker code if 1 single person has an issue

#

If multiple people have issues, then it can be a RunPod issue

#worker no execute