fix: Use mlserver 1.5.0 #5403
Merged
fix: Use mlserver 1.5.0 #5403
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lc525
approved these changes
Mar 6, 2024
| .PHONY: train-all | ||
| train-all: iris huggingface-text-gen-gpt2 huggingface-text-gen-tiny-stories moviesentiment income income-xgb income-lgb download-mnist-onnx download-cifar10-tensorflow wine-mlflow mnist-pytorch |
There was a problem hiding this comment.
Is income-lgb no longer needed? (I see its corresponding make rule has remained in the Makefile)
lgtm otherwise.
There was a problem hiding this comment.
It is still part of the examples we provide, however building a new model with the new lgb library fails because of some api changes in the new library. Given that the old version still works then I thought we can fix this issue later in a follow up PR.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it:
This change upgrades the "default" images for mlserver to point to
1.5.0as it is now released.Note that some models are still using the artifacts generated from mlserver
1.3.5but they work with the new version.I didnt regenerate the notebooks for now but happy to do if required.
Which issue(s) this PR fixes:
Fixes #
Special notes for your reviewer:
Model artifacts are generated and uploaded to seldon public cloud storage
using
~/samples$ make train-all upload-all