-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
fix model builder limited container support for endpoint mode. #4683
Conversation
… containers other than TGI and DJL
if "djl-inference" in image_uri: | ||
logger.info("Building for DJL JumpStart Model ID...") | ||
self.model_server = ModelServer.DJL_SERVING | ||
if "djl-inference" in self.pysdk_model.image_uri: |
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.
can we add huggingface-pytorch-inference
in the image URI matching logic and map ti model server of MMS.
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.
Let's add it next as we may need to add tune capability for it.
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.
no tune function needed for the HF container, the goal is to make it work with local container mode first.
self.pysdk_model.tune = self.tune_for_tgi_jumpstart | ||
elif "huggingface-pytorch-inference:" in self.pysdk_model.image_uri: | ||
logger.info("Building for MMS JumpStart Model ID...") | ||
self.model_server = ModelServer.TGI |
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.
why mapping to TGI? should be MMS right?
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.
Fixed
… containers other than TGI and DJL
Issue #, if available:
Description of changes:
Fix: ModelBuilder limited container support for endpoint mode.
Testing done:
Merge Checklist
Put an
x
in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.General
Tests
unique_name_from_base
to create resource names in integ tests (if appropriate)By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.