What is meant by a runner?
I have created my worker template and I am configuring GH actions. I am just unsure of what
RUNNER_24GB is supposed to be, as to create a serverless endpoints require a container image but building and testing is the point of the CI/CD pipeline?12 Replies
Runner 24gb means that the runner of your ci cd pipeline will be a machine with 24gb of rams i guess...
Where is it from?
for context
GitHub has nothing to do with RunPod so its not really appropriate to ask GitHub questions here.
Use Google etc.
yeah but it would have to be self hosted
😂
GitHub
GitHub - runpod-workers/worker-template: 🚀 | A simple worker that c...
🚀 | A simple worker that can be used as a starting point to build your own custom RunPod Endpoint API worker. - runpod-workers/worker-template
Well you should have mentioned this in the first place instead of expecting people to read your mind.
Your original reply had no thought behind it, it wasn’t remotely helpful. If I could use the internet to answer the question obviously I would. I stated it was a worker template in the first sentence, so I’m not sure why you even replied if you haven’t worked with making worker templates on runpod from scratch (in which case you would have had an idea of what I was talking about).
Sure, we all know where its from, thats why @nerdylive also had to ASK where its from! 🤦♂️
Anyway you are getting blocked now, don't have time for rude people.
Yeah yeah whatever 🤡
in that case... its your endpoint id, once you've created one
Thats the thing, you have to deploy with a container image first, but the point of the CI/CD pipeline is to build and test. Am i wrong?
Ive had to just manually build and test for now
There are no options for building images on RunPod. But, you can build and test it locally. In your docker run command just add a volume to test_input.json like this:
docker run --rm --gpus all -v ./test_input.json:/app/test_input.json myimage
./test_input.json should contain input for your endpoint. This example assumes that your WORKDIR is /app and you must have a GPU on your local system. This will put your image into test mode and it will parse your test_input as if it had been posted to your endpoint.