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.

Sign up for GitHub

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

Jump to bottom

Triton server support with kfserving protocol #2460

Closed
FogDong opened this issue Sep 20, 2020 · 1 comment
Closed

Triton server support with kfserving protocol #2460

FogDong opened this issue Sep 20, 2020 · 1 comment
Labels
triage Needs to be triaged and prioritised accordingly

Comments

@FogDong
Copy link

FogDong commented Sep 20, 2020

We have MLServer to support SKLearn and XGBoost in kfserving protocol, see PR #2450
But it can't cover the case when it comes to triton server and we need a similar approach for implementation: TF_SERVER when using protocol: kfserving

Triton will also need a config.pbtxt file and I'm not sure do we want to automatically generate it or not.

/kind feature
/cc @cliveseldon @adriangonz
@FogDong FogDong added the triage Needs to be triaged and prioritised accordingly label Sep 20, 2020
@ukclivecox
Copy link
Contributor

Triton support for KFServing protocol is now available in 1.3
https://docs.seldon.io/projects/seldon-core/en/latest/servers/triton.html
We don't plan to support TFServer at present as it does not directly support KFServing protocol. Also TF models can be run under Triton.

Can you test.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
triage Needs to be triaged and prioritised accordingly
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ukclivecox @FogDong