-
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
Revert "change: add TGI 2.4.0 image uri (#4922)" #4926
Conversation
This reverts commit 0ea5994.
@@ -76,7 +76,7 @@ Before sending us a pull request, please ensure that: | |||
1. Install tox using `pip install tox` | |||
1. Install coverage using `pip install .[test]` | |||
1. cd into the sagemaker-python-sdk folder: `cd sagemaker-python-sdk` or `cd /environment/sagemaker-python-sdk` | |||
1. Run the following tox command and verify that all code checks and unit tests pass: `tox -- tests/unit` |
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.
Is this correct?
Locally I do tox -e py310 -- tests/unit
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.
This is a revert so we should reland this update later. I think the -e py310 is optional, just points which py version to use
* Enable quantization and compilation in the same optimization job via ModelBuilder and add validations to block compilation jobs using TRTLLM an Llama-3.1. * Require EULA acceptance when using a gated 1p draft model via ModelBuilder. * add accept_draft_model_eula to JumpStartModel when deployment config with gated draft model is selected * add map of valid optimization combinations * Add ModelBuilder support for JumpStart-provided draft models. * Tweak draft model EULA validations and messaging. Remove redundant deployment_config flow validation in optimize_utils in favor of the one directly on jumpstart/factory/model. * Add "Auto" speculative decoding ModelProvider option; add validations to differentiate SageMaker/JumpStart draft models. * Fix JumpStartModel.AdditionalModelDataSource model access config assignment. * move the accept eula configurations into deploy flow * move the accept eula configurations into deploy flow * Use correct bucket for SM/JS draft models and minor formatting/validation updates. * Remove obsolete docstring. * remove references to accept_draft_model_eula * renaming of eula fn and error msg * fix: pin testing deps (#4925) Co-authored-by: nileshvd <113946607+nileshvd@users.noreply.github.com> * Revert "change: add TGI 2.4.0 image uri (#4922)" (#4926) * fix naming and messaging * ModelBuilder speculative decoding UTs and minor fixes. * Fix set union. * add UTs for JumpStart deployment * fix formatting issues * address validation comments * fix doc strings * Add TRTLLM compilation + speculative decoding validation. * address nits --------- Co-authored-by: Joseph Zhang <cjz@amazon.com> Co-authored-by: EC2 Default User <ec2-user@ip-172-16-2-151.us-west-2.compute.internal> Co-authored-by: Gary Wang 😤 <garywan@amazon.com> Co-authored-by: Gary Wang <38331932+gwang111@users.noreply.github.com> Co-authored-by: Erick Benitez-Ramos <141277478+benieric@users.noreply.github.com> Co-authored-by: nileshvd <113946607+nileshvd@users.noreply.github.com> Co-authored-by: Haotian An <33510317+Captainia@users.noreply.github.com>
This reverts commit 0ea5994.
Issue #, if available:
Description of changes:
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.