Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

HTTP Proxy and TFServing should not use the same resource defaults #360

Closed
jlewi opened this issue Mar 6, 2018 · 0 comments
Closed

HTTP Proxy and TFServing should not use the same resource defaults #360

jlewi opened this issue Mar 6, 2018 · 0 comments

Comments

@jlewi
Copy link
Contributor

jlewi commented Mar 6, 2018

Right now HTTPProxy and TFServing both use the same resource defaults.

https://github.com/kubeflow/kubeflow/blob/master/kubeflow/tf-serving/tf-serving.libsonnet#L12

This doesn't make much sense as HTTPProxy probably needs much fewer resources. For example it probably doesn't need as much RAM since it doesn't load the model or GPUs in the case of GPU serving.

It might be worth looking at some examples of using with and mixins e.g.
https://github.com/ksonnet/parts/blob/master/incubator/memcached/memcached.libsonnet

It might nice if we could have a withResources option.

yanniszark pushed a commit to arrikto/kubeflow that referenced this issue Feb 15, 2021
It has been using the cluster where argo ran
elenzio9 pushed a commit to arrikto/kubeflow that referenced this issue Oct 31, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants