-
Notifications
You must be signed in to change notification settings - Fork 834
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
Add support to deploy SKLearn and XGBoost models with MLServer #2450
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
/cc @cliveseldon @RafalSkolasinski @axsaucedo There are still a few details left on this PR, like rebasing once #2023 gets merged, but I think that the rest is ready for review. It would be great to get your thoughts! |
aff0b4f
to
7a8e9f2
Compare
Tue Sep 22 09:24:59 UTC 2020 impatient try |
Tue Sep 22 09:25:00 UTC 2020 impatient try |
Mon Sep 28 10:39:06 UTC 2020 impatient try |
Mon Sep 28 10:39:19 UTC 2020 impatient try |
Mon Sep 28 10:39:21 UTC 2020 impatient try |
/test lint |
Mon Sep 28 11:04:55 UTC 2020 impatient try |
/retest |
Mon Sep 28 13:51:56 UTC 2020 impatient try |
Mon Sep 28 13:51:59 UTC 2020 impatient try |
/test integration |
Tue Sep 29 09:40:19 UTC 2020 impatient try |
Tue Sep 29 09:40:24 UTC 2020 impatient try |
Tue Sep 29 09:40:34 UTC 2020 impatient try |
/test integration |
Tue Sep 29 10:52:05 UTC 2020 impatient try |
Tue Sep 29 10:52:11 UTC 2020 impatient try |
Tue Sep 29 10:52:13 UTC 2020 impatient try |
/test notebooks |
Tue Sep 29 13:22:27 UTC 2020 impatient try |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice one, solid work!
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: RafalSkolasinski The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
/test notebooks |
Wed Sep 30 13:33:31 UTC 2020 impatient try |
Wed Sep 30 15:43:56 UTC 2020 impatient try |
Wed Sep 30 15:44:18 UTC 2020 impatient try |
What this PR does / why we need it:
Add support to deploy SKLearn and XGBoost models compatible with the V2 Dataplane proposed by NVIDIA / KFServing, by leveraging MLServer.
On most cases, the user will be able to enable the V2 dataplane by specifying
kfserving
as the protocol on theirSKLEARN_SERVER
andXGBOOST_SERVER
deployments. For example, one can do:To Do
Add examples with V2 protocol(moved to Add SKLearn and XGBoost examples for MLServer / V2 Dataplane #2479)Which issue(s) this PR fixes:
Fixes #1648
Special notes for your reviewer:
This PR is based on #2023. Once that one gets merged, I'll rebase this one to
master
to clean up Git's history.Does this PR introduce a user-facing change?: